跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+86新增论文
+61其中 AI 相关
+14已有论文修订
+93新增 AI 导读

arXiv 最近完成扫描:2026-11-16 01:34 · 全站最近入库:2026-11-16 10:40各信源进度 →

统计口径与数据新鲜度

统计 2026-11-15 11:17 — 2026-11-16 11:17(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-16 01:34最近发现新增版本:2026-11-16 10:40库内论文最新更新时间:2026-11-13 16:48

每分钟刷新已保存的数据。空检查不代表采集异常;新收录可能包含历史论文。AI 导读按新增版本计数。

23,434 已收录论文19,641 AI 相关6,765 有修订112 HF 社区发现

浏览论文库

时间范围跟随排序:版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常,查看状态 →

找到 23,434 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-16 01:33(北京时间)
新论文 · v1arXiv:2611.14425

量化时间序列基础模型在传感器数据应用中的采样频率不变性

Quantifying the Sampling Frequency Invariance of Time-Series Foundation Models for Sensor Data Applications

Sourish Gunesh Dhekane, Abinaya Kumar, Torsten Woertwein, Yan-Bo Lin, Thomas Ploetz, Shabnam Ghaffarzadegan

AI 速读 基于摘要

该研究对四个主流时间序列基础模型进行压力测试,量化其在采样频率变化下的不变性,并考察性能退化是否与信息带宽损失相关。

cs.LG · cs.AI

查看原文摘要

Time-Series Foundation Models (TSFMs) are increasingly used in sensor applications, where sampling frequency (SF) varies across sensors, devices, and operating modes (e.g., power saving). Ideally, TSFMs must remain effective during such SF changes, provided the SF retains task-critical bandwidth. In this paper, we stress-test 4 prominent TSFMs: MOMENT, Chronos-2, Moirai-MoE, and TimesFM, to quantify their SF-invariance and investigate whether their behavior tracks the resulting loss of information bandwidth rather than the SF value itself. Our stress-test probes 3 dimensions: (i) the shift in embeddings, (ii) the degradation in forecasting performance, and (iii) the degradation in downstream performance, quantified by three novel metrics: FSI, FDI, and CDI, respectively. To our knowledge, this is the first study to place SF-invariance at the core of TSFM evaluations. Our results characterize: (i) how SF-invariance depends on the margin between signal's native-SF and the bandwidth its task requires, (ii) how much of that invariance the choice of TSFM explains, and (iii) how much of TSFM's performance degradation under a lower SF reflects information loss rather than a limitation of their abilities. These findings reframe SF-invariance as a measurable, signal-aware property of the (signal X TSFM) pair, and guide practitioners on when TSFMs display SF-invariance.

新论文 · v1arXiv:2611.14424

DnNP:神经过程中的输入不确定性去噪

DnNP: Denoising Input Uncertainty in Neural Processes

Fatemeh Tohidian, Chengzhi Shi, Soomi Lee, Matthew Elia, Amy Mueller, Stratis Ioannidis, Jennifer Dy

AI 速读 基于摘要

提出DnNP,在神经过程框架中显式建模输入噪声,通过变分推断联合去噪与元学习,以提升含噪输入下的预测与不确定性量化。

cs.LG

查看原文摘要

Neural Processes (NPs) are flexible meta-learning models capable of uncertainty quantification across diverse applications. However, the standard NP framework assumes access to noise-free inputs. This is unrealistic in many practical settings, where sensor noise or measurement errors are unavoidable. This discrepancy between model assumptions and real-world data can significantly degrade prediction quality and uncertainty estimates. We introduce Denoising Neural Processes (DnNPs), a principled extension of the NP framework that explicitly models input uncertainty. We train DnNPs via variational inference. DnNPs jointly learn to denoise corrupted inputs and perform meta-learning, making them robust to noisy training data. We demonstrate DnNPs' effectiveness on both synthetic and real-world datasets, showing consistent improvements in prediction and uncertainty quantification compared to standard NPs. On PM2.5 spatial interpolation from real-world air quality sensors, DnNP reduces RMSE by up to 30% and NLL by up to 73% relative to standard NPs. We also provide theoretical grounding: we show that the Bayes-optimal predictor under noisy inputs belongs to the DnNP model class, and that plug-in models with fixed observation variance incur an irreducible KL divergence gap that DnNP provably avoids.

新论文 · v1arXiv:2611.14422

在量子计算机中加载经典数据的能量代价

The energetic cost of loading classical data in quantum computers

Joao F. Doriguello, Alessandro Luongo, Harshit Verma

AI 速读 基于摘要

作者将经典数据加载视为硬件过程,量化超导处理器上QRAM查询的动态能量代价,并比较两种QRAM架构。

quant-ph · cs.ET

查看原文摘要

Quantum algorithms for machine learning, chemistry, and cryptanalysis often assume coherent access to classical data at negligible physical cost. We instead treat data loading as a hardware process and quantify the dynamic energetic cost of a quantum random access memory (QRAM) query on a superconducting processor. Using the metric-noise-resource framework, we relate query fidelity and power to gate duration, relative two-qubit drive strength, and the distribution of attenuation across a multi-stage refrigerator, while accounting for thermal photons and gate errors. We analyze the linear-depth multiplexer and the noise-resilient bucket-brigade architectures, adapting the latter to a native superconducting gate set and refining its fidelity analysis using the fully decomposed gate schedule. For a representative bucket-brigade QRAM query with a $12$-qubit address register we obtain a query fidelity of $0.969$. The query consumes $3.51\times10^{-4}\,\mathrm{J}$ of dynamic energy, corresponding to an average dynamic power of $4.38\,\mathrm{W}$ and a peak of $64.4\,\mathrm{W}$. Our optimization shows that, at fixed target fidelity, the operating point and attenuation profile can change the average power by a factor of two or more.

新论文 · v1arXiv:2611.14421

Earlybird:2900万参数下的预测式流式语音识别

Earlybird: Predictive Streaming Speech Recognition in 29M Parameters

Sahil Mahendrakar

AI 速读 基于摘要

作者提出一个29M参数的流式语音识别器Earlybird,通过随机截断音频训练,使其能在词尚未说完时提前预测整词并给出置信度。

cs.SD · cs.CL · eess.AS

查看原文摘要

Streaming speech recognizers output a word only after the speaker has finished it, typically 90-400 ms later. For a voice agent every millisecond counts: the sooner the words are outputted, the sooner the agent can start a search or plan its reply. We present Earlybird, a 29M-parameter streaming recognizer (16.8 MB at 4 bits). Earlybird learns from audio cut off at random points, including partway through a word, and is asked to predict every word that is due by then in full, plus a guess of the next two words. Its raw token probabilities give a confidence for every word including the one still being spoken. On clean audiobook speech (LibriSpeech test-clean), the median word is predicted correctly 90 ms before the speaker finishes it, while released streaming models get it 90 to 400 ms after it ends. Earlybird is the earliest on all six test sets we time, covering audiobooks, TED talks, public speech, earnings calls, and synthetic speech. On the same audiobooks, 69% of words are predicted correctly before they end, against 3-25% for the other models. For words still being spoken, confidence is calibrated, with an expected calibration error (ECE) of 3.7 to 5.5. On the eight English Open ASR Leaderboard sets, it is more accurate than Moonshine Tiny on every set and roughly ties Whistle, a model of the same size.

新论文 · v1arXiv:2611.14420

OnlyAct:从基础模型中提取动作表示以构建世界模型

OnlyAct: Extracting Action Representations from Foundation Models for World Models

Runjia Li, Minghao Chen, Junyu Xie, Philip Torr, Andrea Vedaldi, Tomas Jakab

AI 速读 基于摘要

作者提出一种无需动作标签的对比式适配方法,从预训练基础模型 V-JEPA 2 的帧对嵌入中提取动作表示,并尽量剥离场景信息,用于动作条件视频世界模型。

cs.CV

查看原文摘要

Video world models promise general-purpose interactive simulators, but their training is limited by action supervision: action labels are scarce, fragmented across incompatible specifications, and do not scale with the unlabeled video pretraining corpus. A common workaround jointly trains an action encoder to compress consecutive frames into a latent action and a decoder to reconstruct the next frame from the previous frame and that latent, forcing the latent to capture only new information. This has two limitations: learning the action space from scratch can limit generalization to unseen domains, and the bottleneck trades expressiveness for separation, with tighter settings losing nuance and looser ones risking scene leakage under domain shifts. We argue for a different starting point: rather than learning actions from scratch, we start from a pretrained foundation model (V-JEPA 2), whose embeddings of a frame pair already carry substantial action information after large-scale, diverse video pretraining. The remaining challenge is to extract the action while discarding the scene. We propose a label-free contrastive adaptation framework that pulls together frame pairs sharing the same motion under a different scene and pushes apart pairs from the same scene with different motion, reshaping the geometry of the pretrained space without imposing a reconstruction bottleneck. We introduce a unified evaluation protocol along three axes (action expressiveness, scene invariance, and action-conditioned video generation quality) across robot manipulation, camera navigation, game, and driving benchmarks, most of which are unseen during adaptation. Compared with annotation-free latent-action methods, our representations are substantially more expressive while matching their scene invariance, and they yield world models that transfer demonstrated actions to new scenes more faithfully.

版本更新 · v3arXiv:2605.06490

工具性选择:测量LLM智能体追求工具性行为的倾向

Instrumental Choices: Measuring the Propensity of LLM Agents to Pursue Instrumental Behaviors

Jonas Wiedermann-Möller, Leonard Dung, Maksym Andriushchenko

AI 速读 基于摘要

作者提出一个基于终端智能体的低风险真实基准,用于测量模型在任务中为达成目标而采取工具性趋同行为(如自我保全)的倾向,并报告了十个模型的评测结果。

cs.AI · cs.CY

查看原文摘要

AI systems have become increasingly capable of dangerous behaviours in many domains. This raises the question: Do models sometimes choose to violate human instructions in order to perform behaviour that is more useful for certain goals? We introduce a benchmark for measuring model propensity for instrumental convergence (IC) behaviour in terminal-based agents. This is behaviour such as self-preservation that has been hypothesised to play a key role in risks from highly capable AI agents. Our benchmark is realistic and low-stakes, aiming to reduce evaluation-awareness and roleplay confounds. The suite contains seven operational tasks, each with an official workflow and a shortcut whose policy status varies by condition. An eight-variant shared framework varies monitoring, instruction clarity, stakes, permission, instrumental usefulness and blocked honest paths to support inferences regarding the factors driving IC behaviour. We evaluated ten models using deterministic environment-state scorers over 1,680 samples, with trace review employed for audit and adjudication purposes. The adjusted IC rate is 86 out of 1,680 samples (5.1%). IC behaviour is concentrated rather than uniform: two Gemini models account for 66.3% of IC cases and three tasks account for 84.9%. Conditions in which IC behaviour is indispensable for task success result in the greatest increase in the adjusted IC rate (+15.7 percentage points), whereas emphasising that task success is critical or certain framing choices do not produce comparable effects. Our findings indicate that realistic, low-nudge environments elicit IC behaviour rarely but systematically in most tested models. We conclude that it is feasible to robustly measure tendencies for dangerous behaviour in current frontier AI agents.

新论文 · v1arXiv:2611.14419

评估LLM生成的世界模型用于神经符号推理

Evaluating LLM-Generated World Models for Neuro-Symbolic Reasoning

Souhaila Djaffal, Amna Jamal, Gagana Madhugiri Devaraja, Anidipta Pal, Jobst Heitzig

AI 速读 基于摘要

作者构建44个场景基准,检验五个LLM能否将自然语言情境生成为部分可观测随机博弈形式的世界模型,并发现机械有效性不足以保证结构忠实性。

cs.AI

查看原文摘要

Formal world models can support planning, verification, and safety reasoning, but constructing them from open-ended natural-language situations is difficult, particularly in multi-agent settings where several formalizations may be plausible. We study whether five LLMs can generate such world models as partially observable stochastic games and whether mechanical validity is sufficient to establish that the resulting model faithfully represents the intended decision problem. We introduce a benchmark of 44 scenarios spanning game, situational, and cultural settings and evaluate generated world models along three dimensions: mechanical validity, reference-relative structural agreement, and semantic criteria. Across three empirical tracks, we analyze 410 first-pass generations. In the reference-backed game track, 134/135 generated world models pass a strict mechanical audit, yet mean permutation-invariant structural F1 is only 0.366, with just 28/134 mechanically valid models exactly matching the authored reference. In the cultural track, explicitly naming the country changes the generated structural representation for most LLMs while producing only small changes in automated semantic scores. These results show that executability is a necessary but insufficient criterion for LLM-generated world models: models that are mechanically valid can still differ substantially in the structure used by downstream neuro-symbolic reasoning and planning.

新论文 · v1arXiv:2611.14418

按需精度:在小规模本地模型的不确定解码步上提升权重比特数

Precision on Demand: Escalating Weight Bits at Uncertain Decoding Steps in a Small Local Model

Mohammed Nayeem Khan, Logesh L, Aliyas Ahmad Misri

AI 速读 基于摘要

作者在 Qwen3-0.6B 上模拟 8 比特权重、默认用高 4 比特解码,仅在低精度输出分布不确定时把该步重算为 8 比特,并在 GSM8K 上按每 token 读取的权重字节数核算成本。

cs.AI

查看原文摘要

Local decoding usually fixes one weight precision for the whole generation. We study a different allocation: store 8-bit weights, decode with their top 4 bits, and redo a step at 8 bits only when the low-precision output distribution looks uncertain (entropy above a threshold or a small top-two margin). Quantization is simulated, the model is Qwen3-0.6B, and the benchmark is GSM8K. Cost is counted in weight bytes read per token. On 36724 replayed steps the entropy of the low pass ranks argmax flips with AUC 0.93. At a 15% escalation budget it catches 78% of flips and the margin gate 94%, against the 15% expected for a random gate of equal rate (a computed expectation, not a run). In 150 live problems all-high scores 64.0% and all-low 55.3% (McNemar p=0.053). An entropy gate with a 16% escalation rate scores 62.7% at 0.87 of the all-high weight bytes. Its paired difference is -1.3 (-8.0 to +5.3) points to all-high and +7.3 (+0.0 to +14.7) points to all-low (p=0.080), so the live data do not separate the gate from either end. Verified speculation reaches zero KL at similar bytes in the same cost model. A live random control, a thinking-mode phase rule, a second model and live KL were not run.

新论文 · v1arXiv:2611.14415

音频基础模型在音乐相似性中的事后解耦探索

Exploring Post-Hoc Disentanglement of Audio Foundation Models for Music Similarity

Lucas de Souza Brandão, Gabriel da Costa Merlin, Diego Furtado Silva

AI 速读 基于摘要

该研究系统考察如何在不微调冻结预训练音频基础模型的前提下,用条件相似性网络(CSN)的掩码门控实现属性特定的嵌入子空间解耦。

cs.SD · cs.LG

查看原文摘要

Audio foundation models like CLAP, MuQ, and MERT excel at capturing general musical similarity. On the other hand, their entangled latent spaces limit interpretability and fine-grained attribute control. Conditional Similarity Networks (CSN) address this by pairing a backbone representation model with learned masks that gate the embedding space into attribute-specific subspaces. However, existing methods train the backbone from scratch, rather than leveraging pretrained foundation models. We instead present a systematic study of post-hoc disentanglement, adapting CSN to gate frozen pretrained embeddings. We evaluate adding trainable parameters to adapt the embedding under different masking and pooling regimes across two datasets. Our findings show that minimal adaptation capacity is sufficient for post-hoc gating to improve both attribute-specific disentanglement and overall retrieval performance, while pooling, masking, and depth choices yield limited additional gains.

版本更新 · v2arXiv:2610.23966

自适应人工智能实现可泛化的胎儿脑生物测量

Generalizable fetal brain biometry via adaptive artificial intelligence

Yijin Li, Mingxuan Liu, Yi Liao, Le Chang, Hongjia Yang, Kasidit Anmahapong, Xiaotian Hu, Ziang Wang 等 27 位作者

AI 速读 基于摘要

提出解剖引导的测试时自适应框架 BioTTA,从三维胎儿脑 MRI 自动测量 11 项生物指标,并在多中心异质数据上提升测量精度与异常检测能力。

cs.CV

查看原文摘要

Fetal brain biometry provides a quantitative basis for assessing prenatal growth and identifying congenital brain abnormalities. However, comprehensive assessment remains limited by labor-intensive manual measurements and automated models that lose accuracy across imaging sequences and institutions. We introduce BioTTA, an anatomically guided test-time adaptation framework that measures 11 fetal brain biometrics from reconstructed three-dimensional magnetic resonance images. BioTTA adapts pretrained models to individual unlabeled volumes using geometric consistency and atlas priors, without access to source images. In a retrospective study across five centers in China and Switzerland, BioTTA improved measurement accuracy across three out-of-distribution datasets and two network architectures. It reduced mean absolute measurement errors by 46-82% relative to the corresponding models without adaptation, achieving errors similar to those of supervised fine-tuning. Its measurements were mapped onto normative growth trajectories derived from expert annotations, enabling gestational-age-specific assessment through a web-based reporting platform. Across four disease cohorts, the platform achieved 82.1-95.0% accuracy in binary detection of ventriculomegaly or cerebellar abnormalities, with performance similar to that of a senior radiologist. BioTTA provides a practical foundation for standardized fetal brain biometry across heterogeneous imaging settings, supporting scalable prenatal growth assessment and quantitative evaluation of brain abnormalities.

新论文 · v1arXiv:2611.14414

SIGMO:Sigmoid 门控交互感知运动规划

SIGMO: Sigmoid Gated Interaction-Aware Motion Planning

Avinash Singh, Manish Saroya, Fatemeh Cheraghi Pouria, Faizan Tariq, Jovin D'sa, David Isele, Yosuke Sakamoto, Sangjae Bae

AI 速读 基于摘要

提出一种基于多项式 sigmoid 门控的交互感知运动规划器,用解析式让行评分结合滚动时域规划,在密集交互场景中兼顾主动性与防御性。

cs.RO

查看原文摘要

Despite the widespread adoption of autonomous vehicle technologies, reliable navigation within cluttered environments remains arduous due to the necessity of interaction-aware strategies; example scenarios include: narrow passages with multiple agents, lane changing in dense traffic, and crossing unsignalized intersections. These scenarios often require highly proactive strategies, simultaneously demanding interpretability and quick adaptability, which challenge end-to-end and data-driven methods. An effective strategy requires: scalability to multiple agents, adaptability to changes in other agents' behavior, and harmony with surrounding traffic without freezing or becoming overly conservative. To meet these requirements, we present SIGMO, a sigmoid-gated interaction-aware motion planner, with two main contributions. First, we formulate polynomial sigmoid functions that analytically estimate yield scores of surrounding agents using physics-grounded interaction features that capture driving intuitions. Second, we integrate the polynomial sigmoid functions into a receding-horizon planner, which facilitates interaction-aware planning with arbitrary trajectory predictions. We validate SIGMO in interaction-intensive simulations and hardware experiments. The results show that SIGMO balances proactive and defensive behavior while remaining computationally lightweight, serving as a strong baseline in a mobility stack. The simulation and hardware experiment videos are available here: https://sites.google.com/view/sigmoid-polygate.

新论文 · v1arXiv:2611.14413

比特还是排列?在小规模本地语言模型中,把固定推理预算花在权重精度上还是选项顺序平均上

Bits or permutations? Spending a fixed inference budget on weight precision or on option-order averaging in small local language models

Mohammed Nayeem Khan, Logesh L, Aliyas Ahmad Misri

AI 速读 基于摘要

在小规模本地语言模型上比较权重低比特量化与选项顺序平均两种节省/稳健手段的相互影响及固定预算下的性价比。

cs.AI · cs.CL

查看原文摘要

Local language models can save memory by storing weights in fewer bits, and they can reduce sensitivity to the order of answer options by averaging a few reorderings. We ask whether the first makes the second worse, and which is the cheaper way to spend a fixed budget. On Qwen3-0.6B and Qwen3-1.7B with simulated round-to-nearest weight quantization (8, 6, 4 and 3 bits, fp16 reference), read from the logits of the letters A to D on ARC-Easy, ARC-Challenge, MMLU and HellaSwag (300 items each), 6 bits lose no accuracy against fp16 (they score +1.8 (+1.0 to +2.5) and +0.9 (+0.3 to +1.5) points higher, which we do not explain), and 8 bits change it by -0.7 (-1.1 to -0.3) and -0.4 (-0.7 to -0.2) points. At 4 bits the answer-slot skew rises from 0.15 to 0.53 (0.6B) and from 0.07 to 0.12 (1.7B); Gaussian noise at the same weight SNR gives 0.15 and 0.37 (two draws) and 0.19 (one draw), so the control is inconclusive on whether rounding adds slot skew beyond equal-power noise. Flip rates rise but stay below an accuracy-matched baseline of independent uniform errors. Averaging four cyclic orders recovers +12.6 points at 4 bits for 0.6B (+5.3 at fp16). We price bits and passes in one machine-independent unit, weight bytes read times passes. In cost-matched pairs, extra orders beat extra bits only when the weights have 6 or more bits, and the decision table reduces to: use 6-bit weights and spend the rest of the budget on up to four orders, one pass each. Everything is simulated on two small models with the simplest quantizer; a title-level search found no earlier study of quantization together with option order.

新论文 · v1arXiv:2611.14411

算术化 k-正交向量问题的均匀量子平均情形细粒度困难性

Uniform Quantum Average-Case Fine-Grained Hardness of Arithmetized $k$-Orthogonal Vectors

Dhruv Prasad Deshpande, Abhishek Mishra

AI 速读 基于摘要

在量子强指数时间假设(QSETH)下,作者给出算术化 k-正交向量多项式在两类规范素数域上、包含全部初始化开销的均匀量子平均情形细粒度困难性归约。

cs.CC

查看原文摘要

We study exact evaluation of the arithmetized $k$-Orthogonal Vectors polynomial $FOV^k$ of Ball et al. (2017, 2018). For every fixed integer $k \geq 3$, set $d(n) = \left \lceil \log^2 n \right \rceil$. Assuming the basic decision version of Quantum Strong Exponential-Time Hypothesis (QSETH), for every constant $\varepsilon > 0$, no uniform quantum algorithm runs in $O(n^{k/2 - \varepsilon})$ time on every input and evaluates this polynomial correctly with probability at least $3 / 4$ over a uniformly random input in $\mathbb F_{p(n)}^{knd(n)}$ and the algorithm's internal randomness, for all sufficiently large $n$. This holds when $p(n)$ is the smallest prime greater than $n^{k - 1}$ and when it is the smallest prime greater than $n^k$. Our direct reduction combines classical polynomial self-correction with calls to a quantum average-case evaluator. For the smaller prime, random sampling finds an orthogonal tuple with constant probability whenever the count is large enough to wrap around modulo $p(n)$; otherwise, the exact residue determines the answer. For the larger prime, quantum minimum finding and an asymptotic prime-gap bound account for the cost of generating the prescribed field. In view of prior isolation-based reductions permitting small characteristics, we present these results as explicit reductions for the two canonical-prime families, with all setup costs included in the uniform quantum running time. The hardness guarantee concerns single-instance exact evaluation; a matching quantum evaluation algorithm and a quantum proof-of-work protocol remain open.

新论文 · v1arXiv:2611.14408

一个极小直觉主义公开宣告逻辑

A minimal intuitionistic public announcement logic

Philippe Balbiani, Hans van Ditmarsch, Cigdem Gencer, Clara Lerouvillois

AI 速读 基于摘要

作者提出不要求传统合流条件的直觉主义公开宣告逻辑 Lmin 与 Lequ,并报告其相对于相应双关系框架类的可靠性与完全性。

cs.LO

查看原文摘要

We introduce intuitionistic public announcement logics Lmin and Lequ determined by classes of birelational frames where the intuitionistic preorder and the modal accessibility relation do not need to satisfy the confluence conditions traditionally considered within the framework of IPAL. Our logics can be seen as generalisations of IPAL seeing that their language is based on a binary epistemic modality of "relativised knowledge" that allows us to define valid reduction axioms. Our main results are the soundness and completeness of Lmin with respect to the class of all birelational frames and the soundness and completeness of Lequ with respect to the class of all birelational frames where the modal accessibility relation is an equivalence relation.

新论文 · v1arXiv:2611.14407

深度神经模型的因果概念解释

Causal Concept Explanations for Deep Neural Models

Josh Rountree, Pulkit Verma, Oswin So, Chuchu Fan, Julie A. Shah

AI 速读 基于摘要

提出CCW-Net,将中介分析作为训练目标,使概念解释对模型输出具有必要性、充分性与独立性,并用作量化评估工具。

cs.LG · cs.AI

查看原文摘要

Concept-based explanations in neural models are important for the development, certification, and adoption of autonomous systems. Yet, interpretability remains correlational. Without methods to guide and quantify causal relationships between explanations, a concept explanation can be provided without being necessary or sufficient for the observed output thereby appearing correct while misleading. We introduce Causal Concept Wrapper Network (CCW-Net), the first use of interventional mediation analysis from fields such as economics, medicine, and epidemiology as a training objective to align causal effects of concept-based explanations with a model's output. We further apply mediation analysis as an evaluation tool to quantify, per concept label combination, how much of any model's output is causally attributable to each concept explanation. As a training objective, CCW-Net shapes a model's concept representations such that they are both necessary and sufficient for the outputs they are credited with and independent of other concepts' contributions. Counterfactual concept representations anchor a set of causal alignment criteria: necessity, sufficiency, and independence. Necessity drives irrelevant concept effects toward zero, sufficiency ensures relevant concept representations fully reconstruct a model's output, and independence enforces the total effect decomposes linearly across concepts. We evaluate CCW-Net across aircraft control, driving, and image classification. CCW-Net provides a step toward concept-based explanations that are not merely interpretable, but quantifiably causal, supporting safer evaluation, certification, and deployment of transparent and trustworthy neural models.

版本更新 · v2arXiv:2606.12635

CD-RCM:面向反射共聚焦显微镜的可泛化连续深度新视角合成

CD-RCM: Generalizable Continuous-Depth Novel View Synthesis for Reflectance Confocal Microscopy

Tooba Imtiaz, Milind Rajadhyaksha, Kivanc Kose, Jennifer Dy

AI 速读 基于摘要

提出首个针对反射共聚焦显微镜(RCM)的前馈式新视角合成模型 CD-RCM,从稀疏深度采样的 RCM 层叠图像预测中间深度切面,实现连续深度、各向同性的三维可视化。

cs.CV

查看原文摘要

Reflectance confocal microscopy (RCM) provides noninvasive, cellular-resolution "optical biopsies" of human skin in vivo by acquiring en-face images at successive depths, forming a sparse z-stack. Due to optical limitations, these stacks are anisotropic 3D volumes with lateral resolution (0.5 $μ$m) $\sim$6 times higher compared to axial resolution, which is defined by the optical sectioning (3 $μ$m), limiting the interpretation of tissue. Our goal is to provide continuous-depth visualization by interpolating intermediate sections and making the 3D volume isotropic. Such a representation permits arbitrary-direction sectioning, including histopathology-like cross-sectional examination, without requiring per-patient optimization. To that end, we introduce the first RCM-specific novel-view synthesis (NVS) approach, CD-RCM, a feedforward model that predicts realistic, unseen depths from sparsely sampled RCM stacks. Classical neural rendering methods focus on reconstruction from surface-level multi-view observations. In contrast to surface-level camera views, RCM can acquire optically sectioned en-face images of tissue beyond the surface up to 200 $μ$m. However, during visualization of the RCM stacks, observations of the shallower sections (towards the surface) obscure the deeper ones. This unique axial imaging geometry and layer-dependent anatomical organization motivated our development of a tailored architectural and training framework that explicitly accounts for RCM's depth-resolved, occlusive imaging physics. Experiments demonstrate that CD-RCM achieves high-fidelity novel-view synthesis with sub-second inference time.

新论文 · v1arXiv:2611.14401

发现南亚季风降水热力学的方程

Discovering Equations for the Thermodynamics of South Asian Monsoon Precipitation

Savannah L. Ferretti, Jane W. Baldwin, Michael S. Pritchard, Tom Beucler

AI 速读 基于摘要

该研究用符号蒸馏从21年再分析资料中学习可解释的南亚季风降水方程,其解释方差约为常用浮力诊断的1.5倍,并保留约85%的神经网络技巧。

cs.LG · physics.ao-ph

查看原文摘要

South Asian monsoon precipitation depends on the thermodynamic structure of the lower troposphere, but how its ingredients combine to shape precipitation remains unclear, partly because this dependence is nonlocal in the vertical. We use symbolic distillation, which combines neural networks and symbolic regression, to discover interpretable precipitation equations from 21 years of June-August reanalysis data. Neural networks first learn the vertical thermodynamic structure most relevant to precipitation, condensing each variable into a single interpretable feature not tied to a particular vertical grid. Then, symbolic regression derives closed-form equations from these features and the surface state. Our best equation explains 1.5 times as much precipitation variance as a widely used buoyancy-based diagnostic and recovers about 85% of neural network skill while using about a thousand times fewer parameters. Unlike the buoyancy diagnostic, which adds moisture and instability, the equations treat them as competing controls, with the heaviest precipitation occurring when the lower free troposphere is humid. Over ocean, sensible heating is associated with additional precipitation mainly when near-surface air is warm and moist, improving predicted precipitation and its diurnal cycle. Although the learned features were optimized only for precipitation prediction, the equations largely respond to each feature as expected from convective physics, consistent with the reanalysis. These responses reduce the dependence of monsoon precipitation on the entire vertical column to a few simple, testable constraints that could guide data-driven precipitation models to make them more physically consistent.

版本更新 · v2arXiv:2606.30533

在细粒度负载波动下协调严格SLO与低成本

Reconciling Strict SLOs with Low Cost under Fine-Grained Load Fluctuations

Dilina Dehigama, Shyam Jesalpura, Zeyu Xu, Marton Nemeth, Shengda Zhu, Marios Kogias, Boris Grot

AI 速读 基于摘要

Spandana通过将SLO保障与成本优化解耦,在应用VM与FaaS之间逐请求调度,以在细粒度负载波动下兼顾严格SLO、高利用率与低成本。

cs.DC

查看原文摘要

Cloud-based online services face significant sub-second load fluctuations while needing to meet strict Service Level Objectives (SLOs). Cluster operators often over-provision resources to protect SLOs, sacrificing utilization and cost efficiency. Existing reactive and proactive autoscalers, serverless (FaaS) deployments, and VM/FaaS hybrid systems fail to reconcile strict SLO compliance with low cost and high utilization under fine-grained load fluctuation. We introduce Spandana, an architecture that addresses this trade off by decoupling SLO enforcement from cost optimization. A lightweight controller colocated with each application VM enforces SLOs by steering each arriving request between the VM and FaaS. Requests that can meet the SLO stay on the VM; the remaining requests are forwarded to a stock FaaS layer such as AWS Lambda. For cost optimization, Spandana's resource allocator determines the most-efficient VM provisioning by accounting for VM cost, FaaS cost, and traffic volatility, allowing the VM pool to run at high utilization. Our evaluation shows that Spandana maintains strict SLO adherence, achieves 76-86% CPU utilization, and reduces cost by 5-44% over three SOTA baselines.

新论文 · v1arXiv:2611.14399

REAL Loss:面向投机解码的真实期望接受长度优化

REAL Loss: Optimizing Real Expected Acceptance Length for Speculative Decoding

Yu Tian

AI 速读 基于摘要

作者提出 REAL 损失,用路径权重无偏估计并优化投机解码的真实期望接受长度(EAL),在受控损失级对比中优于若干已有目标。

cs.LG · cs.CL

查看原文摘要

Speculative decoding accelerates LLM inference by having a draft model propose multiple tokens for the target model to verify in one pass. The speedup is governed by the expected acceptance length (EAL), yet standard training objectives such as cross-entropy, KL divergence, and total variation focus only on distribution matching or single-step overlap. Recent studies instead propose block-level training objectives, aiming to optimize EAL directly. However, these objectives remain surrogates rather than exact formulations of EAL. For example, some average later acceptance over target-distributed continuations rather than the verification branches selected by accepted tokens, introducing a covariance gap that can reverse the gradient direction. We analyze this gap and derive REAL, a real EAL training loss that uses path weights for unbiased estimation and Rao-Blackwellization for variance reduction. In a controlled loss-level comparison with a Qwen3.6-35B-A3B target and a Domino drafter, REAL outperforms WTV, VSD, DBLast, and the static LK baseline on probabilistic serving acceptance length across 9 task subsets and 5 evaluation seeds. These gains require only a change to the training loss, with no modification to the drafter architecture or inference procedure, demonstrating the practicality of real EAL training. A reference implementation of the REAL loss is available at https://github.com/King-ty/speculators/tree/real-loss.

新论文 · v1arXiv:2611.14604

KernelMosaic: An Open Dataset and Agentic Framework for CUDA Kernel Generation

Ningyuan Xi, Yuhang Lai, Ning Miao

原文摘要

Training large language models to generate efficient CUDA kernels requires supervision spanning diverse computational requirements and iterative code optimization. Constructing this supervision is challenging because of heterogeneous specifications, and useful implementations emerge through iterative complicated testing and refinement. We introduce KernelMosaic, an open dataset pairing diverse CUDA tasks with verified solutions and trajectories. Human-guided review and diversity-aware selection curate tasks expressed as natural-language descriptions, reference programs, mathematical specifications, and their intersections. To build the solutions and trajectories, our agentic framework guides a strong LLM through implementation, correctness repair, and performance optimization with reusable CUDA guidance and execution feedback. Supervised fine-tuning of a small open-source model on KernelMosaic raises correctness from 4%, 0%, and 0% to 88%, 82%, and 16% on KernelBench L1, L2, and L3, respectively, while increasing the fraction of tasks with kernels faster than PyTorch eager at every level. Further training experiments show that supervision from the curated trajectories substantially outperforms direct responses and promotes sustained testing and revision. These results demonstrate that KernelMosaic enables a general-purpose model to achieve substantial gains in CUDA kernel generation.

cs.LG · cs.AI

新论文 · v1arXiv:2611.14397

从间隔视角理解 LoRA:对灾难性遗忘的鲁棒性与适配器合并(MaLoRA)

A Margin Perspective on LoRA: Robustness to Catastrophic Forgetting and Adapter Merging (MaLoRA)

Ziqing Xu, Hancheng Min, Lachlan Ewen MacDonald, Salma Tarmoun, Enrique Mallada, Weijie Su, Rene Vidal

AI 速读 基于摘要

该文在多类线性分类的近正交任务设定下,用间隔(margin)视角理论刻画最优 LoRA 适配器,并据此提出免训练的适配器合并规则 MaLoRA。

cs.LG

查看原文摘要

Low-rank adaptation (LoRA) is the de facto method for parameter-efficient fine-tuning of large neural networks, achieving strong task adaptation with minimal trainable parameters and low optimization cost. Beyond this efficiency, practitioners have observed two striking properties: \textit{robustness to catastrophic forgetting} and the ability to \textit{merge independently trained adapters} into a single model that performs competitively across multiple tasks. These properties are central to continual and multi-task learning, yet remain poorly understood. In this work, we provide a theoretical explanation through a unified \textit{margin-based perspective}. We analyze LoRA in multiclass linear classification under a near-orthogonal task regime with $\ell_2$-regularization, and characterize the optimal LoRA adapter across regularization regimes. Our analysis shows that, in an intermediate regime of regularization parameters, the optimal adapter aligns with the \emph{max-margin solution} on the fine-tuning data. Building on this characterization, we derive two key consequences. First, we obtain closed-form expressions for the margins on pre-training and fine-tuning data, revealing a precise margin trade-off: the regularization parameter controls the balance between retention and adaptation. Second, we analyze adapter merging, proving that merged models achieve positive margin on each task and deriving optimal mixing coefficients that balance margins across tasks and maximize the margin over their union. These results lead to a simple, training-free merging rule, which we term \textit{margin-based LoRA merging} (MaLoRA). Experiments on modern architectures and real datasets validate our theoretical predictions, showing that MaLoRA matches or outperforms several adapter-merging baselines across a range of vision and language classification tasks.

版本更新 · v3arXiv:2606.15893

BALTO:面向幻觉缓解的平衡令牌级策略优化

BALTO: Balanced Token-Level Policy Optimization for Hallucination Mitigation

Ning Li, Zixuan Guo, Yan Xu, Wenbo Fei, Yifan Niu, Chang Luo, Yasheng Wang, Weiwen Liu 等 10 位作者

AI 速读 基于摘要

提出 BALTO 框架,通过将声明级事实核验投影为令牌级标签并引入平衡的令牌级信用分配,缓解大语言模型在知识密集型场景中的幻觉问题。

cs.CL

查看原文摘要

Hallucinations remain a major obstacle to deploying large language models (LLMs) in knowledge-intensive settings, where generated responses must be faithfully grounded in provided evidence. Reinforcement learning (RL) is a promising direction for hallucination mitigation, but response-level faithfulness rewards suffer from a granularity mismatch: localized hallucinations can cause supported content to receive spurious penalties. Although recent work introduces fine-grained feedback such as claim-level verification and token-level rewards, unbalanced credit assignment can still induce length, verbosity, or optimization-noise biases. We propose BALTO, a Balanced Token-level Policy Optimization framework for hallucination mitigation. BALTO extracts checkable factual claims, verifies them against the reference context, and projects claim-level judgments to token-level labels. A balanced token-level credit assignment mechanism is introduced into the framework. This design redistributes probability mass from unsupported content toward faithful content, rather than suppressing the entire response. We systematically analyze the limitations of response-level rewards from a theoretical standpoint, and prove BALTO's advantages in training stability and optimization efficiency for hallucination mitigation. Experiments on ConFiQA, RAGTruth, and FinLLM-Eval show that BALTO achieves the highest faithfulness across all six model--benchmark settings and consistently outperforms existing post-training baselines in Q-Score, demonstrating a stronger faithfulness--informativeness trade-off. The code is released at https://github.com/NingLi670/BALTO.

版本更新 · v3arXiv:2603.13652

基于激活修补的因果归因

Causal Attribution via Activation Patching

Amirmohammad Izadi, Mohammadali Banayeeanzade, Alireza Mirrokni, Hosein Hasani, Mobin Bagherian, Faridoun Mehri, Mahdieh Soleymani Baghshah

AI 速读 基于摘要

提出 CAAP,通过在 ViT 中间层直接替换 patch 的内部激活来估计每个图像块对预测的因果贡献,作者报告其在多个骨干和指标上优于现有归因方法。

cs.CV

查看原文摘要

Attribution methods for Vision Transformers (ViTs) aim to identify image regions that influence model predictions, but producing faithful and well-localized attributions remains challenging. Existing attribution methods face several limitations, with gradient-based, relevance-propagation, and attention-based methods relying on local approximations, while perturbation- or optimization-based methods intervene on inputs, tokens, or surrogates rather than internal patch representations. The key challenge is that class-relevant evidence is formed through interactions between patch tokens across layers; methods that operate only on input changes, attention weights, or backward relevance signals may therefore provide indirect proxies for patch importance rather than directly testing the predictive effect of contextualized patch representations. We propose Causal Attribution via Activation Patching (CAAP), which estimates the contribution of individual image patches to the ViT's prediction by directly intervening on internal activations rather than using learned masks or synthetic perturbation patterns. For each patch, CAAP inserts the corresponding source-image activations into a neutral target context over an intermediate range of layers and uses the resulting target-class score as the attribution signal. The resulting attribution map reflects the causal contribution of patch-associated internal representations on the model's prediction. The causal intervention serves as a principled measure of patch influence by capturing semantic evidence after initial representation formation, while avoiding late-layer global mixing that can reduce spatial specificity. Across multiple ViT backbones and standard metrics, CAAP consistently outperforms existing methods in various settings and produces more faithful and localized attributions.

新论文 · v1arXiv:2611.14389

评估用于传达三维形状的触觉编码策略

Evaluating Tactile Encoding Strategies for Communicating 3-D Shape

MacKenzie C. Harnett, Rebecca F. Friesen

AI 速读 基于摘要

比较两种在二维触觉显示器上编码三维形状的方法(单层高度图与二值分层切片),并对比摩擦调制显示屏与针阵列的表现。

cs.HC

查看原文摘要

Two-dimensional haptic displays, such as programmable pin arrays and vibrotactile or friction-modulating touchscreens, enable tactile communication of complex shapes in a low-profile form factor. However, many shapes of interest, including CAD models, three-dimensional graphs, and map topographies, are inherently three-dimensional. This work investigates two methods for encoding 3-D information using a 2-D tactile display: (1) a single tactile height map providing coarse but quantifiable depth cues, and (2) a series of binary layers communicating sequential slices of a 3-D model, supporting more complex geometries such as overhangs and cavities. We further compare performance across two display types--a friction-modulating display and a pin array--to examine how the level of haptic abstraction affects users' ability to decode discrete 3-D information. A user study demonstrates that participants were able to effectively complete a 3-D assembly task using both strategies, achieving high accuracy across all display types. While the pin array supported faster task completion and higher-rated--though not statistically significant--user experience than the friction-modulating display for the binary-layer task, these differences did not translate to significant differences in overall usability (i.e., reassembly accuracy success). Together, these results identify design trade-offs and inform development of future surface haptic displays that support the communication and interpretation of discrete 3-D information in tactile graphics.

新论文 · v1arXiv:2611.14387

模糊块边界:面向高效扩散语言模型的重叠块去噪

Blurring the Block Boundaries: Overlapping Block Denoising for Efficient Diffusion Language Models

Amir Mann, Jonathan Fhima, Shaked Brody, Or Avitan, Asif Zamir, Shahar Tsiper, Niv Nayman

AI 速读 基于摘要

提出免训练、免超参的 B3 方法,让相邻两个块在同一次前向中并行去噪,以加速自编辑块扩散语言模型。

cs.CL · cs.AI

查看原文摘要

Diffusion Language Models (DLMs) have emerged as effective alternatives to autoregressive models for latency-critical tasks, enabling faster token generation. Recent advances employ block diffusion with self-editing capabilities, where each block refines tokens iteratively before advancing to the next one. Yet each block is only as fast as its slowest token, and the next block cannot start before it. We suggest Blurring the Block Boundaries (B3), a novel method with which two blocks are refined in parallel within a shared forward pass. B3 calibrates itself on the fly, opening the next block only once the model is ready to start generating it. It is a training-free and hyperparameter-free acceleration method which seamlessly integrates within any self-editing block diffusion model. Evaluated on state-of-the-art DLMs across 10 diverse datasets spanning varied tasks and difficulty levels, B3 results in on par generation quality and 11.5-14.5% speedup compared to the base model, pushing the Pareto frontier for latency-quality trade-offs in DLM inference.

版本更新 · v3arXiv:2610.33484

能否听见几何?用于文本到B-rep检索的规范不变谱描述子

Can One Hear Geometry? Gauge-Invariant Spectral Descriptors for Text-to-B-rep Retrieval

Hongzhu Yi, Hao Liu, Tao Yu, Tiankun Yang, Yujia Yang, Zhenghao Zhang, Tianyu Zong, Zhenyu Guan 等 15 位作者

AI 速读 基于摘要

提出 SpectraBRep 框架,用基于几何不变性与谱描述子的方法在跨模态对齐前消除 B-rep 的位姿、尺度与边界编码歧义,用于文本到三维实体检索。

cs.CV

查看原文摘要

Text-to-3D solid retrieval faces a fundamental representation gap: while natural language describes intrinsic shapes, Boundary Representation (B-rep) entangles precise geometry with arbitrary variations in pose, scale, and boundary encoding conventions. Existing methods either discretize B-reps at the cost of analytic precision, or learn features from topological graphs without explicit invariance guarantees. We propose **SpectraBRep** (*Spectral Geometry for Text-to-B-rep Retrieval*), a framework based on geometric invariance and spectral descriptors that mathematically eliminates representation ambiguities prior to cross-modal alignment. Formalizing translation, rotation, reflection, uniform scaling, and contour re-indexing via group actions, we exploit the planar-profile-and-extrusion structure of engineering solids to construct a unified spectral descriptor across cross-sectional regions, contour boundaries, and extrusion depths. On public benchmarks, our method achieves state-of-the-art recall performance across all evaluation metrics.

版本更新 · v5arXiv:2606.18048

在破碎阈值处对非拥挤超图进行列表染色

List coloring uncrowded hypergraphs at the shattering threshold

Abhishek Dhawan, Abhishek Methuku, Minh-Quan Vo

AI 速读 基于摘要

该论文证明了非拥挤超图的列表色数达到由优惠券收集启发式猜测的最优前导常数,并由此推出线性超图染色与调色板稀疏化结果。

math.CO · cs.DM · cs.DS

查看原文摘要

A foundational theorem of Ajtai, Komlós, Pintz, Spencer, and Szemerédi asserts that every $n$-vertex $k$-uniform uncrowded hypergraph (i.e., with girth at least $5$) of maximum degree at most $Δ$ contains an independent set of size $cn(\logΔ/Δ)^{\frac{1}{k-1}}$ for some absolute constant $c>0$. Improving an earlier bound of Frieze and Mubayi, Iliopoulos showed that every such hypergraph has list chromatic number at most $(1+o(1))(k-1)(Δ/\logΔ)^{\frac{1}{k-1}}$. Determining the optimal leading constant in this bound remains a major open problem. A natural target, suggested by the coupon-collector heuristic, is $(k-1)^{\frac{1}{k-1}}$, which also corresponds to the shattering threshold for coloring sparse random hypergraphs. Our main result shows that this target is attained: for every integer $k\ge2$, every $k$-uniform uncrowded hypergraph of maximum degree at most $Δ$ satisfies: $$χ_\ell(\mathcal{H})\le(1+o(1))\Big((k-1)\fracΔ{\logΔ}\Big)^{\frac{1}{k-1}}.$$ In particular, this confirms a 2019 conjecture of Molloy for uncrowded hypergraphs. Building on this result, we prove that every $k$-uniform linear hypergraph of maximum degree at most $Δ$ has chromatic number at most $(c_k+o(1))(Δ/\logΔ)^{\frac{1}{k-1}}$, where $c_k\to1$ as $k\to\infty$, thereby proving a conjecture of Verstraëte and Wilson on the independence number of linear hypergraphs in the stronger form of colorings. Our techniques also yield a palette sparsification theorem for uncrowded hypergraphs, partially answering a question of Casselgren and Eriksson.

版本更新 · v3arXiv:2609.29646

顺序 Phragmén 规则保证 2-近似核心稳定性

Sequential Phragmén Guarantees 2-Approximate Core Stability

Jianan Lin, Chenhao Wang

AI 速读 基于摘要

作者证明经典多项式时间投票规则 sequential Phragmén 在认可偏好下总能选出 2-稳定(2-核心)的委员会,并说明该界是紧的。

cs.GT

查看原文摘要

We study approximately stable committee selection under approval preferences, following Cheng et al.~[EC~2019] and Jiang, Munagala, and Wang~[STOC~2020]. In an approval-based committee election, $n$ voters each approve a subset of the candidates, and a committee of size $k$ is selected. A size-$k$ committee is $λ$-stable if, for every nonempty subset $T$ of candidates, the number of voters who strictly prefer $T$ is less than $λ$ times the proportional share $\frac{n|T|}{k}$. We consider sequential Phragmén, a classical polynomial-time voting rule, and prove that it always returns a $2$-stable committee. This implies that the $2$-core is always nonempty and improves upon the $3.651$-stability guarantee of Gao, Sun, and Vondrák~[EC~2026]. The guarantee also extends to weighted voters and is tight even for unweighted elections: for every $1\leλ<2$, sequential Phragmén can return a committee that is not $λ$-stable. Compared with the exact-core algorithm developed in concurrent work by Becker, Greger, and Peters~[arXiv~2026], sequential Phragmén is simpler to implement, and our proof of its $2$-stability is elementary.

新论文 · v1arXiv:2611.14383

基于能量的视角看机器学习

An Energy-Based Perspective on Machine Learning

Bo Dai, Yilun Du

AI 速读 基于摘要

这篇教程以能量模型(EBM)为统一视角,把判别模型、生成模型、表示学习、强化学习与推理时计算等机器学习方法组织成同一框架,并指出它们主要在三项选择上不同:能量、推断与学习。

cs.AI · cs.LG

查看原文摘要

Energy-based models (EBMs) define a distribution through a scalar energy, $p_θ(x)\propto\exp(-E_θ(x))$, and are usually presented as one model family among many. This tutorial has a broader goal: beyond introducing EBMs, it uses them as a single lens that connects the different aspects of machine learning. Any EBM is specified by three choices, the energy, which determines what the model represents; the inference procedure, which samples from or optimizes the energy; and the learning method, which fits the energy to data. We first develop these components, including sampling, variational inference, and learning by maximum likelihood, noise contrastive estimation, pseudolikelihood, score matching, and adversarial training, and show that the learning methods share one contrastive structure. We then show that discriminative models, generative models such as GANs, normalizing flows, diffusion and autoregressive models, representation learning methods such as contrastive learning, word2vec, BERT, denoising auto-encoders, and diffusion representations, reinforcement learning with EBM policies and world models, inverse reinforcement learning, and planning, as well as inference-time computation with verifiers, are all EBMs that differ in these three choices, mostly in how they handle the partition function and sampling. This view explains existing methods, organizes them into a common framework, and suggests new algorithms by replacing one component while keeping the others, with composition of energies as a principled way to combine learned models at inference time.

新论文 · v1arXiv:2611.14382

大语言模型“通过思考学习”机制的认知映射

Cognitive Mapping of Learning by Thinking Mechanisms in Large Language Models

Dong Han, Jin Zhang, Kunyue Yang

AI 速读 基于摘要

该文提出一个认知LbT框架,把四种“通过思考学习”的认知机制映射到大语言模型的计算过程,并讨论其能力边界与结构性失败。

cs.AI

查看原文摘要

Large language models (LLMs) increasingly exhibit capabilities that resemble human Learning by Thinking (LbT), the acquisition of new insight through internal processes such as explanation and reasoning, without new external input. A systematic account of the cognitive mechanisms behind these capabilities, and of their limits, remains underdeveloped. This paper proposes a Cognitive LbT Framework that maps four mechanisms (Reflective Reasoning, Synthetic Memory Formation, Internal Simulation, and Conceptual Self-Organization) onto computational processes in LLMs. Drawing on representative methods, including chain-of-thought prompting, self-consistency, self-reflection, Tree-of-Thoughts search, Self-Instruct, and self-taught reasoning, the analysis argues that selected methods can functionally approximate aspects of these mechanisms and can improve performance on some tasks without additional labeled examples, although this does not always constitute durable learning in model parameters. For example, Self-Instruct generated approximately 52,000 instructions from 175 seed tasks and reported a 33% absolute improvement on Super-NaturalInstructions (Y. Wang et al., 2023). The same mechanisms also produce characteristic failures, including hallucination diffusion, model collapse, concept drift, and high computational cost. These failures are not isolated technical defects but follow from four structural asymmetries between LLMs and human cognition: the identity of generator and monitor, closed learning loops without external grounding, symbolic rather than sensorimotor simulation, and the cost of inference-time computation. The framework yields testable propositions about when LbT in LLMs should succeed or fail and offers a structured basis for designing more reliable autonomous learning systems.