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

+907新增论文
+744其中 AI 相关
+108已有论文修订
+94新增 AI 导读

arXiv 最近完成扫描:2026-11-19 06:59 · 全站最近入库:2026-11-19 06:59各信源进度 →

统计口径与数据新鲜度

统计 2026-11-18 12:07 — 2026-11-19 12:07(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:2026-11-19 06:59最近发现新增版本:2026-11-19 06:59库内论文最新更新时间:2026-11-18 08:00

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。

26,871 已收录论文22,375 AI 相关8,156 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 22,375 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-19 06:57(北京时间)
版本更新 · v4arXiv:2603.01865

CyclicJudge: Mitigating Judge Bias Efficiently in LLM-based Evaluation

Ziyi Zhu, Olivier Tieleman, Alexey Bukhtiyarov, Jinghong Chen

原文摘要

LLM-as-judge evaluation has become standard practice for open-ended model assessment; however, judges exhibit systematic biases that cannot be averaged out by increasing the number of scenarios or generations. These biases are often similar in magnitude to the model differences that benchmarks are designed to detect, resulting in unreliable rankings when single-judge evaluations are used. We introduce a variance decomposition that partitions benchmark score variance into scenario, generation, judge, and residual components. Based on this analysis, CyclicJudge, a round-robin assignment of judges to scenarios, is demonstrated to be the optimal strategy for a fixed judge panel and judge-call budget: it cancels the average additive judge offsets while matching the cost of single-judge evaluation. Empirical results on MT-Bench and MindEval validate the effectiveness of CyclicJudge as predicted, across both general-purpose and domain-specific evaluation settings, reducing benchmark score variance and stabilizing the resulting model ranking.

cs.CL

新论文 · v1arXiv:2611.05638

VIPBench: A Human-Aligned Benchmark for Voice Identity Perception in the Age of Voice Cloning

Xudong Tang, Matthew Groh

原文摘要

Speaker-recognition benchmarks test how accurately a model recovers the speaker label of a recording, treating voice identity as a property of the person who produced it. However, these benchmarks do not evaluate how humans perceive voice identity. Whether a listener hears two voices as the same person has consequences for intellectual property rights, cybersecurity, and everyday life. We introduce the Voice Identity Perception benchmark (VIPBench), which contains 124,876 same-or-different judgments from 1,290 listeners on 9,800 recording pairs from 100 public figures. The pairs include real recordings, voice clones generated by a text-to-speech system, and morphs between two speakers' voices. We also define four tasks that evaluate the alignment between speaker-representation models and human identity perception. The first two tasks measure how well a model's similarity score predicts the proportion of listeners who respond "same" and the majority response. The other two measure whether a model and listeners find the same speaker pairs similar, and whether a model's relationship to listener judgments holds equally for real and synthetic recordings. We evaluate eleven publicly available speech models. Listener judgments diverge from speaker labels most often for voice clones: in 41% of responses, listeners judged a clone and a real recording of the same speaker to be different people. No model reaches the noise ceiling; the best model explains 61% of the explainable variance. Models trained with speaker labels align with listeners better than self-supervised models do, yet a model with a 12% error rate on speaker labels aligns with listeners as well as models with error rates below 2%. VIPBench enables the evaluation of speaker models against human perception on real, cloned, and morphed speech, and our results motivate training speaker models directly on listener judgments.

cs.SD · cs.AI · cs.CY · cs.MM

新论文 · v1arXiv:2611.05636

Route to Remember: Adaptive Memory Selection for LLM Agents

Zeyu Fang, Jun Yin, Yongsheng Mei, Xu Han, Chaitali Joshi, Zhongkai Sun, Jie Hao, Bin Guo 等 11 位作者

原文摘要

The memory of production agents is increasingly becoming a bottleneck and is built almost exclusively from text: key points are extracted from out-of-limit context and retrieved into context at query time. Therefore, every new query incurs an additional cost that grows with the accumulated history. Weight memory is a complementary alternative that internalizes knowledge into model parameters and answers with no context at all, and has recently proven effective in self-evolving agents for internalizing skills and behaviors. However, its application in episodic and semantic memory, such as user-specific facts, remains comparatively unexplored, and a gap remains between earlier attempts at weight memory and text-based systems regarding recall performance. We study how to make weight memory competitive as a long-term factual store by applying on-policy self-distillation (OPSD). It trains a context-free student from a teacher, which is the same model conditioned on the user's memory, together with a verify-then-regenerate router that lets weight and text memory each cover the queries they handle best. On the HaluMem benchmark, OPSD matches or surpasses strong text-memory baselines, including full-context prompting and retrieval systems, while reading fewer tokens per query. We further conduct an extensive study that characterizes the behavior of weight memory and analyzes how different training recipes affect its performance. As agent harnesses move toward persistent, multi-session deployments, these results position weight memory as a practical, low-cost component of agent memory and provide insights into feasible training and evaluation protocols for combining it with retrieval.

cs.AI

新论文 · v1arXiv:2611.05633

Spatio-Temporal Multi-Order Interaction for Video Recognition

Kevin D. Nguetche, Lilian Hollard, Eric Granger, Marco Pedersoli

原文摘要

Many temporal approaches for video recognition rely on explicit cross-channel aggregation projections, which have quadratic complexity in the number of channels, introducing significant computational overhead. In addition, the spatio-temporal representation used for video recognition is biased either toward local order interactions (for CNNs) or toward global order interactions (for transformers). Starting from the multi-order spatial representation of MogaNet, our method introduces two complementary contributions to tackle these problems. First, for the temporal modelling, we introduce parallel multi-order processing with depthwise-only convolutions and implicit gating-based aggregation, which is linear in the number of channels, inducing a considerable computational reduction. Second, we propose a dual interaction between spatial and temporal dimensions, which allows a better spatio-temporal representation without increasing the computational cost. By combining these two contributions, our proposed VideoMogaNet achieves performance on par with or better than state-of-the-art action recognition approaches across multiple video benchmarks (UCF101, HMDB51, Kinetics-400, Diving48), while considerably reducing the cost of the temporal branch.

cs.CV · cs.AI · cs.LG

新论文 · v1arXiv:2611.05632

Assurance-Conditioned Continuous Authorization for Autonomous AI Agents

Mehdi Shajari

原文摘要

Autonomous software agents can act through tools, delegate work, and change their models or execution environments while earlier authorizations remain in flight. We present Assurance-Conditioned Continuous Authorization (ACCA), an approach designed to be harness-independent, for maintaining operational authority according to currently justified assurance. It distinguishes evidence validity from contextual applicability, derives assurance claims from eligible evidence, and resolves a multidimensional effective-authority envelope within a principal-declared ceiling and applicable policy. A typed dependency graph supports selective re-evaluation of authorization-relevant changes. An authority epoch changes when effective authority changes; a distinct optional authorization-basis version supports revalidation of action-specific authorization conditions. Protected effect-time enforcement can reject stale actions before a consequential resource change, subject to the available commit mechanism. A compositional Domain Governance Profile expresses domain-specific semantics without granting authority. Controlled scenario tests implemented as a regression suite using a trading profile exercise default-deny rules, evidence-conditioned contraction and recovery, policy divergence, selective non-response, and stale-action rejection at a local gateway before the simulated-broker boundary. The study establishes implementation-level evidence in one domain, not a cross-domain guarantee of harmful-behavior prevention.

cs.AI · cs.CR

版本更新 · v3arXiv:2508.09275

Constrained Black-Box Attacks Against Cooperative Multi-Agent Reinforcement Learning

Amine Andam, Jamal Bentahar, Mustapha Hedabou

原文摘要

Collaborative multi-agent reinforcement learning (MARL) is increasingly deployed in critical domains, yet its vulnerability to adversarial perturbations has not been thoroughly investigated. Most existing adversarial attacks against MARL rely on optimistic assumptions, such as access to policy weights or the ability to train surrogate policies. We investigate whether adversaries with limited capabilities remain effective against MARL agents. In particular, we study two restricted attack settings that are overlooked in the literature: (i) adversaries with access only to agent observations and (ii) adversaries with no access whatsoever. Our approach generates perturbations that intentionally misalign how victim agents perceive their environment, preventing them from collaborating. We conduct extensive experiments across a diverse set of 22 environments. Our results demonstrate both the effectiveness and sample efficiency of our attacks.

cs.LG · cs.MA

新论文 · v1arXiv:2611.05626

Exact signal recovery from generative priors with sigmoid output activation

Matthew S. Scott, Yaniv Plan, Özgür Yılmaz

原文摘要

We show exact signal recovery in generative compressed sensing for feedforward neural networks with piecewise-linear activations and a final sigmoid activation, with no assumption of expansivity. Consider a ReLU network of depth $d$ with a sigmoid final activation, whose input layer, of dimension $k$, is the narrowest, and let $K$ be the geometric mean of the widths of its layers. We show that, with high probability, all signals of the range whose entries lie in $[δ, 1 - δ]$ are uniformly recovered from $m \gtrsim k(d \log(K/k) + \log(1+\log(1/δ)))$ measurements.

cs.IT · eess.SP · stat.ML

版本更新 · v3arXiv:2606.11319

Neural networks become centroid classifiers when trained on heavily corrupted inputs

Justin Tahmassebpur, Asadullah Bhuiyan, Hyejin Kim, Omri Lesser

原文摘要

Learning from imperfect data is a central theme in machine learning, connecting practical questions of robustness to fundamental questions of learnability. Here we examine attribute noise: learning from corrupted inputs while keeping the labels intact, a setting that has received considerably less analytical attention than its label-noise counterpart. We consider two types of corruption models: additive noise and replacement noise. Through experiments with multi-layer perceptrons (MLPs) on corrupted classification datasets, we find that neural networks remain robust, maintaining well-above-chance accuracy even when inputs are >90% corrupted -- far beyond human recognition. To understand this robustness, we analyze infinite-width networks in the heavy-corruption regime using a mean-field-inspired approach and derive a leading-order decision rule for the classification outcome: the network implements a prototype rule, the nearest-class-mean, assigning each test point to the class whose training-set average it most closely resembles. This leading-order decision rule is universal across a broad range of MLP architectures, holding for any depth, as well as a wide class of activation functions and noise distributions. The same centroid mechanism closely matches finite-width network behavior in our experiments and provides an interpretable and analytically tractable account of why learning can succeed even when individual training examples carry almost no signal.

cs.LG · cond-mat.dis-nn

版本更新 · v2arXiv:2610.21257

Fractional Power-of-Two Quantization for Efficient and Effective Multiplier-Free LLM Inference

Sunghyun Wee, Geunjae Choi, Hyeonjin Kim, Suyoung Kim, Nojun Kwak

原文摘要

Large Language Models (LLMs) demand efficient inference, where the multiply-accumulate (MAC) operations in linear projections dominate compute and energy cost. Post-training quantization (PTQ) reduces this cost by mapping weights and activations to low-bit integers. Power-of-Two (PoT) weight quantization promises efficient multiplier-free LLM inference via shift-add logic, but suffers significant accuracy degradation at low bit-widths due to its coarse base-2 quantization grid. We introduce Fractional PoT (FPoT), a base-$\sqrt{2}$ (half-octave) fractional PoT grid that achieves practical 4-bit weight quantization while preserving a fully integer shift-add datapath. The method combines (i) the base-$\sqrt{2}$ weight grid with uniform integer activations, (ii) a calibration-time grid-alignment refinement absorbed into the static per-channel scale, and (iii) a lightweight 1-adder $\sqrt{2}$ approximation whose error is absorbed during weight calibration via approximate-grid quantization, yielding a processing element (PE) with significantly fewer gates than a 4-bit integer multiplier. On Llama-3-8B with 4-bit weight and activation quantization, FPoT improves zero-shot commonsense reasoning performance by 8.72% relative to the PoT baseline, while maintaining performance close to the uniform integer baseline, with only a negligible 0.4%p degradation. These results hold across various configurations spanning seven models and three bit-widths. Furthermore, FPoT can be integrated with state-of-the-art LLM PTQ methods, demonstrating framework-agnostic applicability.

cs.LG · cs.AI

版本更新 · v2arXiv:2609.09502

Recovery Theory for Projected Power Iterations in Permutation Synchronization

Vahan Huroyan, Gilad Lerman

原文摘要

We study the projected power method for permutation synchronization: recovering $n$ unknown permutations of $m$ objects from pairwise relative permutations, observed independently with probability $p$ and independently corrupted by uniform permutations with probability $1-π_0$. Our main theorem establishes uniform one-step contraction for all estimates with optimally aligned block-error fraction at most $1/2-ε$, for fixed $ε>0$, including measurement-dependent estimates. When $np\ge C_0\log(n)$ and $m=o(npπ_0^2)$, one update contracts the error by a factor $O(m/(npπ_0^2))$, up to a floor of $O(e^{-c\min\{m\,npπ_0^2,\,npπ_0\}} + \log(n) / n)$. Thus, every initialization in this majority basin achieves $o(1)$ error after one update and maintains it uniformly over subsequent iterations. A reference-block spectral initializer enters the basin with probability $1-o(1)$, yielding end-to-end almost-exact recovery. If additionally $\min\{m\,npπ_0^2,\,npπ_0\} \ge C\log(n)$ for sufficiently large $C$, the method achieves exact recovery in finitely many iterations. We also establish prescribed-block recovery under weaker conditions for measurement-independent estimates and extend the guarantees to independent permutation-valued corruptions with uniform mean and to partial permutations with common visible support.

stat.ML · cs.IT · math.OC

版本更新 · v3arXiv:2507.10880

Domain-Adaptive Small Language Models for Structured Tax Code Prediction

Souvik Nath, Sumit Wadhwa, Luis Perez

原文摘要

Every day, multinational firms process thousands of transactions, each of which must adhere to tax regulations that vary by jurisdiction and are often nuanced. The determination of product and service tax codes, such as HSN or SAC is a major use case in Tax compliance. An accurate determination of such codes is imperative to avoid any tax penalties. This paper proposes a domain-adaptive small language model (SLM) with an encoder-decoder architecture for the enhanced prediction of product and service tax codes. In this approach, we address the problem of predicting hierarchical tax code sequences using unstructured product and services data. We employ an SLM based upon encoder-decoder architecture as this enables sequential generation of tax codes to capture the hierarchical dependencies present within the tax codes. Our experiments demonstrate that encoder-decoder SLMs can be successfully applied to the sequential prediction of structured tax codes, a domain that remains comparatively unexplored in current NLP research. In this paper, we demonstrate the superior performance of the domain-adaptive encoder-decoder SLMs over flat classifiers when applied to the Harmonized System of Nomenclature (HSN), and achieve superior results compared to decoder-only and encoder-only architectures for structured sequence generation tasks. This approach can also be scaled to other government-mandated tax commodity codes, such as United Nations Standard Products and Services Codes (UNSPSC), or Brazil's Nomenclatura Comum do Mercosul (NCM).

cs.LG · cs.CL

版本更新 · v5arXiv:2512.20773

DIAL: Direct Iterative Adversarial Learning for Realistic Multi-Turn Dialogue Simulation

Ziyi Zhu, Olivier Tieleman, Caitlin A. Stamatis, Luka Smyth, Thomas D. Hull, Daniel R. Cahn, Jinghong Chen, Matteo Malgaroli

原文摘要

Realistic user simulation is crucial for training and evaluating multi-turn dialogue systems, yet creating simulators that accurately replicate human behavior remains a significant challenge. An effective simulator must expose the failure modes of the systems under evaluation. This work introduces Direct Iterative Adversarial Learning (DIAL), an adversarial framework that iteratively enhances user simulator realism through a competitive dynamic between a generator (user simulator) and a discriminator. When applied to mental health support, a domain characterized by diverse failure types and a critical dependence on realistic user behavior for failure detection, DIAL restores lexical diversity diminished by supervised fine-tuning and drastically reduces discriminator accuracy. The resulting simulator exhibits a strong correlation between simulated and real failure occurrence rates while maintaining low distributional divergence of failure modes. These findings indicate that DIAL is a promising method for developing realistic user simulators in multi-turn dialogue, facilitating reliable and cost-effective system evaluation prior to deployment.

cs.CL

版本更新 · v2arXiv:2610.38970

Communication-Efficient Clustered Federated Learning in Non-IID Wireless Networks

Martin Isaksson, Rickard Cöster, Šarūnas Girdzijauskas, Seif Haridi

原文摘要

Current and emerging mobile networks face increasing privacy, scalability, and performance challenges as distributed learning becomes essential for advanced 6G services. These challenges are amplified by the presence of non-IID data, naturally arising in heterogeneous wireless environments, that degrade the performance of standard Federated Learning (FL) approaches. To address non-IID data across clients, we propose a Clustered Federated Learning (CFL) framework that assigns clients to specialized models during training. Data-domain clustering initializes model-based clustering, enabling identification and exploitation of client similarities without sharing raw data while reducing communication cost. Motivated by mmWave beam selection, we evaluate our methods on a wireless simulation dataset (DeepMIMO) and complement it with two non-IID benchmarks (FEMNIST, Rotated CIFAR-10) to isolate different non-IID characteristics. Our best configurations improve accuracy over IFCA by 4.8 pp on DeepMIMO and 10.6 pp on FEMNIST while reducing downlink data volume by 83.1 % on FEMNIST compared to IFCA. We demonstrate that different clustering strategies suit different non-IID characteristics. These results show that our CFL methods enable resource-efficient, and high-performance distributed learning in future 6G networks.

cs.LG

版本更新 · v3arXiv:2607.17082

OTAP: Structure-Aware Optimal Transport for Evaluating Planning and Execution in Agent Trajectories

Babak Barazandeh, Subhabrata Majumdar, George Michailidis

原文摘要

Large language model agents solve tasks by generating trajectories that interleave planning, tool calls, and intermediate results. Current evaluation metrics reduce such a trajectory to a binary success flag, compare it against a reference by exact matching, or delegate judgment to another language model. A success flag cannot distinguish sound solutions from lucky ones, nor explain why runs fail. Exact matching penalizes valid plans reordered or decomposed differently. We reframe trajectory evaluation as a distance between the agent's execution graph and a set of valid solution graphs, and instantiate it via an unbalanced fused Gromov-Wasserstein transport problem over attributed dependency graphs. The resulting score, termed OTAP (Optimal Transport for Agentic Planning), is a normalized discrepancy score. Its idealized, globally minimized entropy-free objective is invariant to dependency-preserving relabelings of a fixed graph and has a redundant-insertion sensitivity analysis under stated assumptions. Its unbalanced marginals handle missing or hallucinated steps without forcing a match; granularity invariance remains an open problem that soft coupling mitigates only in part. On controlled perturbations and three public benchmarks, OTAP separates valid from invalid trajectories in a regime where semantics-only metrics score below chance. Its performance is encouraging across these settings, while controlled edge-noise experiments reveal sensitivity to dependency extraction. Where a formal verifier exists, strict surface metrics predict validity better than OTAP does, which places OTAP in open-ended domains where no verifier is available. A blinded study of 236 trajectories finds the strongest agreement with OTAP among the six compared metrics. Structure-aware baselines achieve higher clean-graph AUROC, while OTAP has the smallest absolute AUROC decline under the tested edge noise.

cs.AI · cs.CL · cs.LG

新论文 · v1arXiv:2611.05620

ViBench 2.0: A Benchmark for Long-Horizon Software Building

Daniel Furman, Preeya Kirani, Ibrahim Sheikh, Zhen Li, Peter Zhong, Michele Catasta

原文摘要

On Replit, our agentic engineering platform, users now build entire products without writing code, through successive feature requests to an agent. Yet existing coding benchmarks evaluate single, fully specified tasks, and many are near saturation. We introduce ViBench 2.0, a benchmark for long-horizon software building that we use to select our platform's models. Its 17 full-stack web products, modeled on widely used software, grow over 241 feature requests and are judged only when finished, as a user would judge them: a browser agent runs 544 test plans, and a build passes only if every plan does, under a grading protocol validated to keep this strict score reliable. Evaluating nine models, we find a reliability gap: the three strongest pass up to 98% of test plans yet deliver a fully working product in at most 65% of builds, and no open-weight model delivers one. The gap is closing fast: across three releases of one model family, pass@1 on the public products rises from 3% to 53% while the cost per build falls by more than half. We release eight products with the harness and grader, hold out nine, and report lessons from production use.

cs.AI · cs.SE

版本更新 · v2arXiv:2611.02197

Conditional Diffusion-Based Generation of T2-Weighted Prostate MRI for Clinically Significant Prostate Cancer Classification

Xavier Rafael-Palou, Alejandro Vergara-Richart, Ignacio Iborra Roncales, Carmen Prieto-de-la-Lastra, Andreu Antolin-Redondo, Juan Morote, Ana Jimenez-Pastor

原文摘要

Scarce and unrepresentative training data limit the performance of prostate MRI prediction models. Synthetic T2-weighted (T2W) MRI may augment training data containing clinically significant prostate cancer (csPCa) and transition zone (TZ) lesions. In this retrospective, single-center, ethics-committee-approved study, we developed a conditional generative model for T2W prostate MRI extending MAISI-v2 with csPCa class, zonal, and lesion-mask-guided conditioning, incorporating a relative advantage weighted loss fine-tuned on 1,303 patients (1,654 lesions). Fidelity was assessed by incremental ablation, and downstream utility was evaluated with T2W-based csPCa classifiers across five simulated training-data scenarios, each testing 18 synthetic-data configurations. The proposed model reduced Fréchet inception distance (FID) from 13.28 (pretrained MAISI-v2) to $2.04 \pm 0.06$ internally (PI-CAI: $3.83 \pm 0.51$). Synthetic augmentation significantly increased AUC in all five scenarios (+0.027 to +0.088; adjusted $p = 0.016$--$0.043$), though cross-institutional augmentation of PI-CAI yielded a non-significant gain (+0.013; $p = 0.397$). Overall, our model improved T2W MRI fidelity, and synthetic images improved csPCa classification under simulated data constraints, although benefit did not transfer significantly across institutions.

cs.CV

新论文 · v1arXiv:2611.05616

LACS: Distribution-Sensitive Label-Agnostic Confidence Selection for Dynamic Data Pruning

Heejin Choi

原文摘要

Training on large datasets motivates selecting which examples receive expensive training computation. Fixed quotas determine the amount of pruning in advance, while absolute confidence cutoffs depend on the score scale. We study a population-relative alternative that adapts the threshold and retained count together. We introduce LACS (Label-Agnostic Confidence Selector), a training-time rule based on maximum predictive confidence, requiring neither labels at selection time nor per-example gradients. LACS removes examples at or above a log-mean-exp reference plus a margin. We characterize its sensitivity to score gaps and mass, and derive an exact no-pruning condition. For $0<ρ<1$, the removed fraction is at most $ρ$ and at least one example remains. The unsigned score permits both confidently correct and confidently wrong examples to be removed. Seven evaluation settings include neural training, language modeling, and boosting. Neural execution studies reduce backward-active rows by 10-35%; on CIFAR-10, 29% fewer backward rows accompany accuracy means of 89.77% versus 89.82% for full CE. At a matched backward budget and number of optimizer updates, LACS is 1.0 pp above small-batch training and 1.2 pp above random selection over five seeds. Across 14 tabular datasets, quadratic boosting reduces mean test error from 23.36% to 22.96%. Its full training replays use about 30% fewer fitting rows; these counters span a different horizon from validation-selected accuracy. In one RBF-SVM case study, elapsed time falls by 37% with slightly lower error. These findings separate selective-work reduction from realized acceleration: the current exact-current-score neural implementation uses an additional scoring forward, so its backward sparsity does not yet translate into wall-clock acceleration. This overhead is an execution choice rather than a requirement of the selection rule.

cs.LG

新论文 · v1arXiv:2611.05615

$\mathcal{C}^\infty$ Smooth Trajectory Planning with Application to Soft Robots

Reinhard M. Grassmann, Abdulaziz Y. Alkayas, Lingyun Chen, Sami Haddadin

原文摘要

High motion performance and avoiding structural vibrations rely on smooth trajectory planning. The smoothness requirement depends on the robot's complexity in terms of the number of degrees of freedom and system order due to the flexibility of the joints and links. For industrial robots, the smoothness requirements have been determined and subsequently taken into account. Although unknown for soft continuum robots, the exact smoothness requirement can potentially be much larger than previously considered ones such as $\mathbf{\mathcal{C}^4}$ for collaborative robots and $\mathbf{\mathcal{C}^5}$ for quadcopter drones. To address this gap, we introduce a $\mathbf{\mathcal{C}^\infty}$-smooth trajectory generator that respects defined kinematic limits and generates infinitely differentiable trajectories. The generated path addresses and generalizes to all smoothness requirements, where a transition between sequential states is needed. Therefore, all trajectories have continuous velocity, acceleration, jerk, snap, crackle, pop, etc. Of particular interest is the case of null boundary conditions, i.e., all derivatives at the start and end of the trajectory are equal to zero. We verified and evaluated our proposed approach in simulations and on hardware.

cs.RO

新论文 · v1arXiv:2611.05611

Hybrid Spark: Adaptive Speculative Decoding That Lets the Content Choose the Drafter

Ekagra Ranjan, Bharat Venkitesh

原文摘要

Speculative decoding (SD) speeds up large language model (LLM) serving, but its gain depends on the workload's \emph{shape}, such as batch size and context length, and on its \emph{content}. A model-based drafter proposes a short block on any content, while a model-free drafter such as n-gram lookup proposes long copies at almost no cost when the output repeats its input, as in code editing. Adaptive verification spends a batch-wide verification budget on the draft tokens most likely to be accepted, but it supports only one model-based drafter. Model-free drafters provide no per-token confidence, so they cannot take part in budget allocation, and deployments must either fix one drafter or split their GPUs between drafters. We present \sys, a framework that runs a model-based and a model-free drafter on every step and gives each request the better of their chains, within adaptive verification and entirely on the GPU, which keeps asynchronous scheduling intact. The key idea is a price per verified draft token: the goodput that slot would earn elsewhere in the batch. Once the model-free drafter's tokens carry calibrated acceptance estimates, fit once on general text, this price puts both drafters' chains on one scale. Instantiated with \dspark and an n-gram drafter in vLLM, \sys achieves 1.10--1.62\x the output throughput of \dspark on code editing at batch size~4 and 1.04--1.27\x at batch size~128, while staying at 0.97--1.01\x of it on chat at temperature~0. A single deployment can therefore serve both workloads.

cs.AI

版本更新 · v2arXiv:2611.02170

Restrained Diffusion Bridges: Targeted Denoiser Training and Refinement

Xuanxi Zhang, Kevin S. Cheng, Weizhou Wang, Aaron R. Dinner, Jonathan Weare

原文摘要

Diffusion models are often inaccurate in critical, data-sparse regions of the target distribution. Sampling from restrained distributions, biased distributions used in classical enhanced sampling to concentrate data near chosen configurations, can control where training data are collected but biases the learned distribution. We establish that this bias cancels exactly when forward noising from restrained data is conditioned on the restrained configuration at an appropriately chosen intermediate time. This allows a pretrained model fine-tuned on restrained data to achieve high accuracy in any chosen region of the target distribution, regardless of its probability, using standard denoising or flow matching objectives without importance weights. When no target data are available, Gibbs sampling enables inference from a model trained exclusively on restrained data.

cs.LG · physics.chem-ph

版本更新 · v2arXiv:2609.13734

PolicyMem: Geometric Policy Memory for LLM Governance

Yuanchen Bei, Zhengzhang Chen, Yanjun Zhao, Haoyu Wang, Hanghang Tong, Haifeng Chen

原文摘要

Effective LLM governance extends beyond detecting unsafe responses to guiding their correction through closed-loop assessment, revision, and verification. Learning-based guards provide strong semantic discrimination but often leave policy knowledge implicit in trained parameters, limiting its explicit reuse across stages. Programmable guardrails make policies explicit through prompts and workflows, but rely heavily on manual engineering to operationalize them. This motivates explicit policy representations that are both learnable and reusable across governance operations. To this end, we introduce PolicyMem, a geometric policy memory that compiles natural-language policies into learnable low-rank subspaces for reuse across governance stages. A policy assessor projects query-response representations onto these subspaces, producing evidence that directly mediates safety judgments and policy attribution. A response rewriter uses the implicated policies to revise unsafe responses, with the same assessor re-evaluating the revised responses. Beyond inference, the same memory constructs training data from model-generated candidates to supervise the rewriter without external teacher calls. Across five widely used benchmarks, PolicyMem achieves the best average unsafe-behavior detection performance among representative baselines while supporting effective policy attribution, rewriting, and post-intervention assessment through the shared policy memory.

cs.CL · cs.AI

新论文 · v1arXiv:2611.05609

On the Generalization Limitation of On-Policy Distillation for Post-RL Consolidation

Yichen Wang, Yufa Zhou, Siqi Zhu, Haozheng Luo, Jingzhi Bao, Zhichao Liu, Zijun Wei

原文摘要

Multi-teacher on-policy distillation (MOPD) extends on-policy distillation (OPD) to consolidate capabilities from multiple teachers. Although prior work reports near-perfect in-distribution (IND) distillation performance, we find that this can mask incomplete capability consolidation beyond the supervised distribution. A preliminary study on synthetic reasoning shows that OPD does not fully transfer teachers' generalization capabilities. We then extend this investigation to real-world tasks, evaluating extrapolative and compositional generalization across mathematical reasoning, coding, agent, and long-context capabilities using Qwen3 models. Across extrapolative settings, OPD and MOPD reach 96.04-102.73% of their teachers' IND scores. Yet their out-of-distribution (OOD) scores remain 2.45-16.25% below the base model's. Across three compositional settings, MOPD improves IND performance over the base model, but its performance on composed tasks as OOD remains 18.19-24.34% below that of the best teachers. To understand these gaps, we examine teacher capability and data coverage as two potential bottlenecks. Jointly alleviating these bottlenecks eliminates OOD forgetting in our experiments and suggests the potential for generalization beyond the teacher. (M)OPD also reduces OOD forgetting on average relative to its reinforcement learning (RL) baselines. Analysis of the associated update geometry reveals smaller and more spectrally concentrated updates on average than those of the RL baselines, along with greater shared update structure under MOPD. Motivated by these findings, we propose geometry-based patching and base-preserving replay to improve OOD performance while largely preserving IND performance. Our findings identify a blind spot in capability consolidation via (M)OPD, highlighting the need for algorithms that explicitly support OOD retention and generalization.

cs.LG

版本更新 · v2arXiv:2606.19544

Reliability without Validity: A Systematic, Large-Scale Evaluation of LLM-as-a-Judge Models Across Agreement, Consistency, and Bias

Justin D. Norman, Michael U. Rivera, D. Alex Hughes

原文摘要

LLM-as-a-Judge has become the dominant evaluation paradigm for language models, but judge validation in practice relies on exact-match agreement, a metric that does not correct for chance and systematically overstates discriminative ability. We present the largest systematic evaluation of LLM-as-a-Judge to date: 21 judges from nine providers across MT-Bench, JudgeBench, and RewardBench, evaluated under three protocols (agreement, consistency, bias audit) over 118 runs and approximately 541,000 individual judgments. Four findings emerge, consistent across the full cohort, including the April 2026 frontier: kappa deflation between exact match and Cohen's kappa is universal (33--41 pp on MT-Bench), judge rankings shift by up to 14 positions across benchmarks, high test--retest reliability (>0.95) coexists with severe position bias (>0.10) in two production-deployed judges (instantiating a consistency--bias paradox), and verbosity bias is small (<0.011) across our cohort under a single pairwise rubric. We distill these into a Minimum Viable Validation Protocol.

cs.CL

版本更新 · v2arXiv:2607.05017

Hyperparameter Transfer in Graph Neural Networks

Gage DeZoort, Boris Hanin

原文摘要

The performance of deep learning models crucially depends on the settings of hyperparameters like learning rate, initialization scale, and weight decay. Hyperparameter transfer aims to make near-optimal hyperparameter settings consistent across model scale, so that large models can be optimized by proxy tuning their smaller, cheaper-to-optimize counterparts. While transfer principles are well-studied in the context of dense neural networks in language and vision tasks, they remain comparatively under-explored for graph neural networks (GNNs). We develop and validate a transfer parameterization for GNNs trained with SGD, Adam, and AdamW. Through theoretical scaling analyses and controlled experiments, we show that the proposed parameterization yields stable feature updates, learning rate transfer, and improved performance as width and depth increase. For SGD, we identify graph-dependent first-layer correction factors and show that their use can accelerate early training in graphs with sparse bag-of-words inputs. For Adam, we explore how different message passing normalizations affect early- and late-training transfer behavior, illustrating the importance of message passing normalization and advocating for an associated hyperparameter. For AdamW, we adapt a parameterization that allows for the joint transfer of weight decay and learning rate. Together, these results provide a practical recipe for scaling GNNs across a variety of learning tasks and training scenarios.

cs.LG · cs.AI

版本更新 · v2arXiv:2610.27279

A latent control model for realistic rodent motion

Aidan Sirbu, Charles Y. Zhang, Yuanjia Yang, Bence P. Ölveczky, Talmo D. Pereira, Blake A. Richards

原文摘要

The development of embodied models of animal behavior is a major goal of the neuro-AI community. Embodied models will enhance our ability to make direct comparisons between biological and artificial agents. To make such comparisons effective, though, we need embodied models that actually move like animals. Previous work has developed virtual animal bodies and techniques for training realistic motion through imitation. However, to date, there is no system for embodied animal modeling that produces natural movements both during trained goal-directed behavior, and during exploration driven by random generation. Here, we introduce Simulated Control via Augmented Motor Priors for Embodied Reinforcement learning (SCAMPER), a system for training an embodied virtual rat model, enabling natural movements during both goal-directed behavior and random exploration. SCAMPER uses a variational architecture with two distinct priors, a motion prior for control and a behavior prior for exploration. We show that combining both of these priors allows SCAMPER to generate realistic behavior during exploration and exploit the task structure effectively. SCAMPER can also learn from sparse rewards as a result of the diverse movements induced by the behavior prior, allowing the system to model realistic sparse-reward tasks from experimental neuroscience. Altogether, SCAMPER provides the neuro-AI community with an effective new system for training embodied models of rodents on realistic tasks.

cs.AI · cs.LG

新论文 · v1arXiv:2611.05605

Transport along Local Annealing Paths: Wasserstein Geometry and Multimodal Sampling

Han Chen, Sifan Liu

原文摘要

Variational approaches to learning transport maps for multimodal sampling can suffer from mode collapse. One way to mitigate this problem is to learn transport along a prescribed path of intermediate distributions defined by geometric annealing. We show that annealing can take a substantial detour in Wasserstein space: when mass moves between modes, the path can be much longer than the distance between its endpoints. We further link path geometry to transport learning, showing that long annealing paths can slow population optimization, while sufficiently regular paths permit rapid convergence. Motivated by these findings, we propose componentwise annealed transport (CAT) to reduce the need for mass transfer between modes. Starting from a mode-informed mixture reference, CAT constructs an exact mixture decomposition of the target and learns separate transport maps along componentwise annealing paths. We estimate the component weights separately and show that these estimates remain consistent even when the learned flows are inexact. We also develop adaptive annealing schedules guided by transport effort. Experiments on multimodal synthetic distributions and Bayesian inference problems demonstrate improvements in transport learning and sampling efficiency.

cs.LG · stat.CO · stat.ML

版本更新 · v2arXiv:2605.26969

Recon: Reconstruction-Guided Reasoning Synthesis for User Modeling

Alan Zhu, Mihran Miroyan, Carolyn Wang, Andrew Zhou, Lisa Dunlap, Narges Norouzi, Joseph E. Gonzalez

原文摘要

User modeling aims to use language models (LMs) to mimic an individual's behavior from a corpus of past context-action pairs (e.g., conversation turns), enabling the simulation of users in settings like behavioral science, human-AI collaboration, and market research. Recent approaches augment these corpora with synthesized reasoning traces, typically generated by conditioning on both context and action. However, action-conditioned traces are post-hoc rationalizations and need not reflect the user's underlying decision process. We propose Recon, which uses action reconstruction to score reasoning traces by their predictive power: given a context and candidate reasoning, a reconstruction model predicts the action, and reconstruction fidelity determines reasoning quality. Across four domains, Recon achieves a 54.7% win rate over Backward Synthesis, a standard post-hoc rationalization baseline. Further, we find that training a reasoning synthesis model with rewards derived from Recon improves downstream user modeling performance, achieving a win rate of up to 70.0% over baselines. We further show that Recon-synthesized reasoning transfers across models, and improves user modeling beyond the reconstruction model. Our work demonstrates that post-hoc rationalization is insufficient for reasoning synthesis, and that useful and interpretable reasoning should naturally elicit the action from the context.

cs.CL · cs.AI

新论文 · v1arXiv:2611.05601

RIDGE: State-Conditioned Reward Blending for Behavioral Coverage in Deep RL Game Agents

AL Muqshith Mohammed Shifan, Kevin Christopher Chua, Ali Neshati, Loutfouz Zaman, Cristiano Politowski

原文摘要

A deep RL agent trained on a fixed persona reward plays one way: an Explorer keeps exploring while starving, a Survivor hoards on an empty map. Since each persona fixes its own reward, automated playtesting trains N agents for N styles. Changing reward composition mid-episode runs into the switching-stability dilemma: PPO degrades under non-stationary rewards. We present RIDGE, a single-agent architecture that sidesteps the dilemma with two design choices: a state-conditioned blender that computes softmax-normalized sigmoid weights from slow-moving state variables, and a multi-head critic that trains one value head per persona on its own stationary signal. On Crafter with four personas, one \ridge agent acquires both branches of the wood-tier crafting/combat split that no fixed-persona baseline solves jointly, and a sharpness ablation confirms state-conditioning drives the gain. We position these results as demonstrations of the blending mechanism's dynamics across n=3 seeds per condition; larger multi-seed sweeps remain future work.

cs.LG · cs.SE

新论文 · v1arXiv:2611.05599

CAPTOR: text-encoder-free grounding by counting caption co-occurrence over the visual words of a frozen encoder

Elad Yoshai, Natan T. Shaked

原文摘要

Grounding a text query in an image needs a matrix scoring every term against every patch. Vision-language models compute it with an aligned text encoder, which many image encoders, such as histopathology-related models trained on slides alone, lack. The Caption-Anchored Patch-Term Occurrence Representation (CAPTOR) estimates the matrix without a text encoder. It clusters a frozen image encoder's patch tokens into visual words and describes each captioned image by its share of patches in each word. A term signature is the standardized difference of those shares between images whose captions mention the term and the rest. The matrix factorizes into a term-by-word table and a query-independent image factor, so an image is encoded once and a new term adds one table row. Against every training-free baseline, CAPTOR leads on Common Objects in Context (COCO), Pascal Visual Object Classes (VOC) and Cityscapes. On COCO, scored on the cells one object owns, it reaches 0.565 mean intersection over union (mIoU) against 0.502. On all three, it is also level with a text alignment trained on the same backbone, which needs gradients, a text encoder and several times the captions. On held-out breast-cancer slides, it exceeds the strongest baseline scoring patches with a pathology text encoder by 0.160 mIoU. Read through CAPTOR, UNI, an encoder trained on slides alone, exceeds such baselines by 0.132 on a common grid. Counting can therefore give a text interface to any image encoder trained without language, wherever captioned images exist.

cs.CV

新论文 · v1arXiv:2611.05596

RAGCompass: Generalizable Retriever Routing via Reranking

Valentin Six, Mufei Li, Dongqi Fu, Yinglong Xia, Hong Li, Pan Li

原文摘要

Different retrievers exist for retrieval-augmented generation, yet none performs best for all queries. Therefore, the key question is: given a query and retrieved passages from different retrievers, which one is most suited for that query? Existing routers usually make predictions from query-specific features and a fixed pool of retrievers; such routers have no output for an unseen retriever and are incapable by design on a new corpus. To fill these gaps, RAGCompass reads the retrieved passage sets themselves: passages from an unfamiliar retriever or corpus stay directly comparable to other passages, so routing stays well designed where a query-only map would fail. We contrastively fine-tune a reranker against the answer each evidence set produces, which accounts for most of the gain; a small comparison head adds a moderate improvement, and neither component has retriever-specific parameters. RAGCompass improves answer F1 by 28% relative to the best fixed retriever, and outperforms fusion baselines, three query-only routers, and a prompted 8B language model. Generalization experiments show that RAGCompass keeps most of its gain under an unseen corpus, retriever, or reader, while query-only baselines fall to the best fixed retriever or below.

cs.CL · cs.IR