跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

覆盖计算机全学科，以 AI 为快捷入口。关注方向、作者和关键词，把发现变成持续的研究积累。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+1072新增论文
+845其中 AI 相关
+94已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-09 13:24 · 全站最近入库：2026-11-09 13:22各信源进度 →

统计口径与数据新鲜度

统计 2026-11-08 14:08 — 2026-11-09 14:08（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：2026-11-09 13:24最近发现新增版本：2026-11-09 13:22库内论文最新更新时间：2026-11-07 02:59

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。

18,172 已收录论文15,506 AI 相关4,527 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

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 3,609 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-09 13:22（北京时间）
版本更新 · v3arXiv:2605.06505

PACZero: PAC-Private Fine-Tuning of Language Models via Sign Quantization

Murat Bilgehan Ertan, Xiaochen Zhu, Phuong Ha Nguyen, Marten van Dijk, Srinivas Devadas

原文摘要

Differentially private (DP) zeroth-order (ZO) fine-tuning of large language models (LLMs) inherits DP's harsh utility-privacy trade-off. PAC Privacy, an instance-based notion, offers an alternative. It bounds the mutual information (MI) between the secret input and the output, and calibrates the noise to the stability of the output under the input distribution. We introduce PACZero, a family of ZO fine-tuning mechanisms under PAC Privacy. For stability, PACZero quantizes each update to a single bit, the sign of the ZO update aggregated over the secret subset of the training data. On many steps all candidate subsets agree on this sign, so the bit can be released at no cost in MI. On the remaining steps the bit passes through a noisy channel calibrated to a per-step MI budget. We study two channels, the standard additive Gaussian channel of PAC Privacy (PACZero-AGC) and a binary asymmetric channel with optimal bit flipping (PACZero-BAC), along with their zero-budget versions at $\mathrm{MI} \to 0$, PACZero-AGC$_0$ and PACZero-BAC$_0$. At zero MI, nothing released during training, including the fine-tuned model, carries any information about which secret subset was sampled, so no adversary inferring that subset can do better than its prior. In particular, the success rate of any membership inference attack (MIA) is bounded by 50% under a balanced prior. To our knowledge, this is the first such guarantee for LLM fine-tuning, and DP matches the MIA bound only at $\varepsilon = δ= 0$ and infinite noise. We evaluate on SST-2 and SQuAD with models from 1.3B to 8B parameters, under LoRA and full fine-tuning. Both channels retain high utility under tight MI budgets, and even PACZero-BAC$_0$, which guarantees zero MI, stays within 2 points of non-private ZO fine-tuning with the same number of steps. To our knowledge no DP method achieves usable utility matching this MIA-resistance level.

cs.LG · cs.AI · cs.CR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09175

SIFR: Stable Signed Flow Reinforcement

Runlong Liao, Xingqian Xu, Lizhang Chen, Baiyu Su, Yufan Huang, Zhonghao Wang, Akash Gokul, Ming-Yu Liu 等 10 位作者

原文摘要

Reward-based fine-tuning of flow models requires effectively promoting high-reward and suppressing low-reward samples, while maintaining training stability over many rounds of iterative updates. Iterative reward fine-tuning provides a simple starting point, but the positive reward weights give no explicit unfitting signal, and repeated reweighting concentrates the distribution and causes collapse. We propose Stable Signed Flow Reinforcement (SIFR), which replaces the reward weights by signed advantages to supply the missing unfitting signal, and constrains the velocity drift from a reference model to stabilize the updates, with a Lagrange multiplier that adapts the regularization strength to a prescribed drift budget. We further show that existing flow RL methods fall within this framework: they implicitly minimize the signed loss, differing in their regularization choices. We validate SIFR on SD3.5 Medium (2.5B) and FLUX.2 Klein (9B) and scale it to Cosmos 3 Super Text2Image (64B): across all 12 backbone--reward pairs with preference and rule-based rewards, it matches or exceeds existing methods, reaches their peak rewards much faster, and keeps improving over long training where they plateau or collapse.

cs.LG · cs.AI · cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09173

TOFS: Feature Selection with Swap Supervision for Semantic Communication over Fading Channels

Zhiyi Zhu, Eiji Takimoto, Patrick Finnerty, Chikara Ohta

原文摘要

Task-oriented semantic communication transmits task-relevant features to support receiver inference under limited communication resources and adverse channel conditions. For image classification, the usefulness of a feature depends on the other transmitted features and the distortion introduced by the wireless channel. Effective feature prioritization should therefore account for classification performance after transmission of the selected features. This paper proposes a Task-Oriented Feature Selection (\textit{TOFS}) framework and method, which evaluates feature replacements using receiver classification loss. Loss differences confirmed under independent transmission samples provide pairwise ranking supervision for a selector network. The trained selector predicts priorities in a single forward pass. CIFAR-10 simulations demonstrate improved classification accuracy over an importance-based feature selection baseline at the same transmitted feature count and average transmit power. The proposed \textit{TOFS} framework shows 84\% accuracy performance under Rayleigh fading and Gaussian noise, compared with the 68\% performance of a SOTA method.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09163

Beyond the Grid: Continuous Dictionary Pursuit for Interpretable Signal Decomposition

Nick Janssen, Melanie Schaller, Bodo Rosenhahn

原文摘要

Deep learning models achieve high accuracy in signal processing but remain difficult to interpret. Classical matching pursuit and sparse coding offer better transparency but suffer from spectral leakage and grid mismatch when signal frequencies do not align with discrete dictionary atoms. We introduce Continuous Dictionary Pursuit (CDP), a framework for interpretable signal decomposition that learns the parameters of closed-form functions directly from data. CDP optimizes over a continuous manifold of differentiable atoms and, unlike prior continuous pursuit methods that operate on a single analytic family, searches a heterogeneous library spanning periodic, trend, transient, and discontinuous structures. The algorithm employs a greedy iterative strategy using data-driven priors and gradient-based optimization to isolate individual signal components, with discontinuous waveforms made differentiable through spectral sharpness annealing. To ensure a sparse atom set for reconstruction, the framework utilizes a stopping criterion based on a predefined atom budget and residual error convergence. Evaluations on synthetic and real-world datasets show that CDP removes the grid discretization error for atom families contained in its library, recovers generative parameters to within $1\%$ on stationary synthetic signals expressible in that library, and achieves the best sparsity-accuracy trade-off among classical, continuous-pursuit, and neural baselines in the sparse regime. Beyond decomposition, we demonstrate that the extracted atoms can serve as structured curriculum targets for training sequence models, improving forecasting accuracy over standard end-to-end training on most evaluated datasets. The method offers a glass-box alternative for signal decomposition by providing high reconstruction fidelity alongside direct physical interpretability.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09156

Evaluation of a Multi-Link Machine Learning Approach for Rainfall Detection Using Satellite Microwave Links

Mostafa Ftouni, Margherita Spalla, Matteo Colli, Andrea Randazzo, Christian Gianoglio

原文摘要

The impacts of climate change have increased the need for reliable real-time rainfall monitoring systems. This study investigates rainfall detection using a network of opportunistic sensors based on satellite microwave links (SMLs) combined with machine learning (ML) classifiers. Two models, a random forest (RF) and a convolutional neural network (CNN), were trained on aggregated SML data, including information from neighboring links. The results demonstrate that leveraging information from multiple links substantially enhances the detection of both wet and dry periods compared to single-link approaches. Moreover, the RF model consistently provides a more stable and reliable trade-off than CNN, improving rainfall detection and reducing misclassifications overall, with particularly strong performance during harsh weather conditions. The study spanned up to 32 rainy days between 2021 and 2024.

cs.AI · cs.LG · eess.SP

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2610.32955

Measure Before You Train: Typed Decision Models vs. a Classical Baseline vs. a Generative LLM for Routing a Personal Multilingual Inbox

Federico Lucca

原文摘要

Personal email agents decide, for every message, its type and urgency and whether to draft a reply, create a task or ignore it. In production these decisions are delegated to a generative LLM or to rules, and their error rate is rarely measured: the stored labels were written by the system itself. We describe Foyer, a self-hosted personal inbox agent, and a measurement protocol -- stratified sampling, frozen snapshots, thread-grouped splits, secret redaction, human labels in the review loop -- that produces ground truth before any training. On 231 emails in Italian and English we compare eleven systems: the production rules, a TF-IDF + logistic-regression baseline, local and hosted typed decision models (Tev1, Nimble, Jeva, Jev) and generative LLMs (Qwen2.5, Gemma 4). Four results. The production rules for message type score 28% against a 57% majority class. With about two hundred labels a logistic regression has the highest accuracy on every field (type 0.79, urgency 0.74, needs-reply 0.83, is-noise 0.90) at a latency three orders of magnitude lower, though it never predicts the two rarest types; the best zero-shot system reaches 0.74 on type. The sender's relationship to the owner is recovered from other emails of the same contact with 98.6% accuracy on the 63% of emails whose sender was seen before: it belongs in the contact graph, not in the prompt. Per-email accuracy is not the product metric: composed into actions, the baseline ignores 18% of the emails that needed a reply or a task, against 4% for the best generative model; a cost-chosen threshold cuts that to 6% and makes the classifier the cheapest system at every price. An adversarial third round (722 emails) with eleven pre-registered hypotheses confirms seven and refutes four. Two blind annotators agree with the reference at kappa 0.81 and 0.86 on type. We release the protocol and the harness; the emails stay private.

cs.CL · cs.HC · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.05516

Dominant-Layer ZO: A Single Layer Dominates Zeroth-Order Fine-Tuning of LLMs

Wanhao Yu, Ziyan Wang, Zheng Wang, Abeer Matar Almalky, Yihang Zuo, Shuteng Niu, Sen Lin, Adnan Siraj Rakin 等 10 位作者

原文摘要

Zeroth-order (ZO) optimization enables memory-efficient fine-tuning of large language models (LLMs) using only forward passes, but it remains unclear how useful adaptation is distributed across layers. In this work, we reveal a surprising phenomenon: ZO fine-tuning is sharply dominated by a single decoding layer. Across multiple LLM families and downstream tasks, fine-tuning this dominant layer alone consistently matches or even exceeds full-model ZO fine-tuning. We further show that the dominant layer is task-agnostic but model-specific, and can be identified before training through a simple inference-only analysis of activation outliers. Specifically, the dominant layer consistently aligns with the first activation-outlier layer in the pre-trained model. To explain this phenomenon, we analyze how perturbation effects propagate under ZO optimization. We find that the dominant layer combines two key properties: high perturbation sensitivity and early placement in the residual stream, allowing perturbation-induced effects to propagate and accumulate through remaining subsequent decoding layers. As a result, this layer produces disproportionately strong and stable optimization signals under forward-only updates. Extensive experiments on LLaMA2-7B and Qwen3-8B across nine benchmarks show that dominant-layer ZO fine-tuning improves average performance over full-model MeZO and LoRA-based ZO fine-tuning while achieving up to 4.52$\times$ training speedup.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09145

Augmentron: Scalable Multi-View Visual Augmentation for Robot Learning

Tanay Tandon, Aseem Doriwala, Jade Choghari, Catherine Weaver, Pragna Mannam

原文摘要

Robot policies trained on visually narrow demonstrations can become sensitive to environmental features that are unrelated to the task. Existing generative augmentation methods can introduce visual diversity, but processing every frame and camera view independently is computationally expensive and may produce inconsistent observations across cameras and timestamps. We introduce Augmentron, a geometry-aware pipeline that generates reusable scene representations and renders them through recorded camera poses. This produces temporally and multi-view consistent environ- ment and workspace variations while preserving the robot, task objects, actions, and annotations. Across three physical manipulation tasks, replacing half of the real world training dataset with Augmentron data improves model success across three tasks for both in out-of-distribution distractor objects, and out-of-distribution workspace variation evaluations. In a separate comparison against alternate augmentation techniques, Augmentron achieves the highest pooled success in all three conditions. The results show that introducing augmented data to a data training recipe can help policies generalize to dynamic real-world settings.

cs.LG · cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09142

Learning Generative Dynamics for 3D Molecule Generation via Sequential Neuro-Symbolic Constraints

Zhuoran Li, Xu Sun, Chang Wen Chen, Wanyu Lin

原文摘要

Diffusion models have recently emerged as a powerful paradigm for generating 3D molecules. Despite showing remarkable promise, they learn atomic distributions implicitly from data, without explicitly encoding physicochemical rules into their generative dynamics. Consequently, generated samples can be statistically plausible yet chemically invalid. To address this problem, we propose Sequential Neuro-Symbolic Constrained Diffusion (SensDiff), a framework that integrates symbolic rules into generative modeling, enabling the model to internalize scientific priors during training. Central to SensDiff is the observation that the diffusion trajectory of 3D molecule generation exhibits a coarse-to-fine evolution: valid molecules arise by first mitigating macroscopic geometric conflicts and then refining structures toward microscopic chemical consistency through iterative denoising. Accordingly, SensDiff mirrors this dynamic by sequentially enforcing constraints with adaptive weighting during training, progressively steering generation toward valid molecular geometries. Moreover, SensDiff translates domain knowledge into interpretable generative controls, grounding opaque neural denoising in scientific principles. Experiments on molecular benchmarks and real-world constrained generation tasks confirm that SensDiff consistently improves chemical validity while adhering to physicochemical rules and user-specified targets. The code is publicly available at https://github.com/WanyuGroup/NeurIPS2026_SensDiff.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v5arXiv:2511.21638

Iterative Policy Optimization: Batch-Online Multi-Turn RL via Single-Turn RL

Daniel R. Jiang, Ankur Samanta, Yukai Yang, Jalaj Bhandari, Rémi Munos, Tyler Lu

原文摘要

Practical LLM agents often operate over multi-turn conversations where success is determined only after the full interaction ends. Most multi-turn RL methods train via on-policy rollouts, but unlike in single-turn RL, the policy cannot produce a trajectory alone, since an external environment must respond after each agent turn. For conversational agents, this environment is a user, but real users are generally unavailable inside the training loop and simulated users are difficult to build faithfully. Separately, real-world deployment is rarely fully online or fully offline. The common production pattern is called batch online, where the current policy is deployed to collect a batch of interaction data, then retrained on that batch and redeployed. We show that this batch-online setting creates an opportunity for applying the classical approximate policy iteration algorithm. Our central observation is that running standard token-level, single-turn GRPO with a learned turn-level $Q$-function as the reward model is a policy improvement step for the multi-turn problem. Building on this, we present Iterative Policy Optimization (IterPO), which alternates between fitting $Q^π$ from logged Monte Carlo returns via standard reward modeling (policy evaluation) and running single-turn GRPO against $Q^π$ (policy improvement). During policy improvement, the learned $Q^π$ scores candidate responses by their expected downstream return, avoiding the need for simulator rollouts of the remaining conversation. Overall, this allows us to do principled multi-turn RL using only single-turn RL methods without an interactive environment or user simulator inside the training loop. We demonstrate the effectiveness of IterPO on six multi-turn negotiation environments.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2605.00020

AirFM-DDA: Air-Interface Foundation Model in the Delay-Doppler-Angle Domain for AI-Native 6G

Kejia Bian, Meixia Tao, Jianhua Mo, Zhiyong Chen, Leyan Chen

原文摘要

The success of large foundation models is catalyzing a new paradigm for AI-native 6G network design: wireless foundation models for physical-layer design. However, existing models often operate on channel state information (CSI) in the spatial-temporal-frequency (STF) domain, where multipath components are superimposed and structurally entangled. This hinders the learning of a universal channel representation. Their reliance on global attention also incurs prohibitive overhead. In this paper, we propose AirFM-DDA, an Air-interface Foundation Model in the Delay-Doppler-Angle (DDA) domain. AirFM-DDA reparameterizes CSI into the DDA domain to resolve multipath components along physically meaningful axes and employs window-based attention with frame-structure-aware positional encoding. Extensive experiments demonstrate transferability across scenarios, tasks, datasets, and antenna configurations. For channel prediction and estimation, AirFM-DDA generalizes zero-shot to unseen cities, achieving average normalized mean-square error (NMSE) gains of 4.9-8.5 dB over the strongest baselines. With only 10% labeled data, it achieves average gains of 12.0 percentage points in Top-1 accuracy for beam prediction and 3.4 percentage points in F1 score for line-of-sight (LoS) identification. It further transfers across simulated datasets and adapts to measured data and different antenna arrays. Compared with global attention, window-based attention reduces training and inference costs by nearly an order of magnitude.

cs.LG · cs.AI · cs.IT · eess.SP

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09141

Circuit Theory-Informed AI for Condition Monitoring in Power Electronics

Yubo Song, Pascal A. Schirmer, Subham Sahoo

原文摘要

Artificial intelligence for power electronics is evolving toward a deeper comprehension of system intrinsic behaviors and dynamics. As a novel integration of neural computation and electric circuits, spike-based neuromorphic computing offers promising potential in high energy efficiency and adaptability for data-driven applications. Building on the latency-coding principles, this article proposes a framework for data-light condition monitoring that relies solely on three-phase AC current measurements. The AC current signals are encoded as membrane potentials of RC-based spiking neurons, which are inherently compatible with spiking neural networks that can effectively facilitate the estimation of device parameters. Case studies are presented to validate the performances, while constraints and further optimizations are also evaluated and discussed, and future extensions of the methodology are provided.

cs.ET · cs.AI · cs.LG · cs.NE · eess.SY

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09140

SPDMX: Large-Scale Open Stem Audio From Symbolic Music

Phillip Long, Eduardo Escoto, Julian McAuley, Zachary Novack

原文摘要

Large public datasets have driven recent progress in machine learning, from text and vision to speech and general audio. Music remains an outlier, as copyright blocks redistribution of training audio, while many modern tasks need individual stems rather than mixtures. Existing multitrack resources trade off realism, scale, and licensing, while synthetic alternatives rely on proprietary VSTs or naive open rendering that yields weak stems. We introduce SPDMX, a listening-guided rendering of public-domain PDMX scores into an openly-licensed stem corpus with aligned scores and an open render pipeline: $253{,}982$ songs, $490{,}159$ mono stems, and $5{,}469$ song-hours at $44.1$ kHz under CC BY 4.0, with paired MIDI and identifiers linking to PDMX metadata. $88{,}403$ songs ($34.8\%$; $2{,}734$ song-hours) provide multitrack supervision. To our knowledge, this is the largest openly-licensed synthetic multitrack subset by song-hours, enabling source separation, stem-conditioned synthesis, MIDI-to-audio, transcription, and joint symbolic-audio modeling. We release the corpus, metadata, and open pipeline for reuse on other symbolic collections. Demos and experimental notes are on the project page.

cs.SD · cs.AI · cs.LG · cs.MM · eess.AS

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09138

Deep Learning Theory through the Lens of Statistical Physics: A Topical Review

Wei Huang, Youjin Deng

原文摘要

The recent success of foundation models and deep learning has far outpaced our theoretical understanding of how large-scale neural networks learn and generalize. Statistical physics provides a natural language for describing such high-dimensional, nonlinear, and strongly coupled systems, offering concepts such as mean-field theory, phase transitions, energy landscapes, and stochastic dynamics. In this topical review, we adopt a statistical-physics way of thinking -- from concepts including phases and criticality, and free-energy viewpoints, to methods such as kernel and Gaussian-process limits, mean-field and dynamical mean-field theories, random-matrix tools, and Fokker-Planck formalisms, and to a mindset emphasizing universality, scaling, and tractable limits with explicit validity regimes. We survey recent progress on understanding modern deep learning through this lens, including mean-field analyses of wide networks, spectral and geometric perspectives on loss landscapes, stochastic-gradient-based training viewed as a dynamical process, and phase-transition analogies that organize phenomena such as overparameterization, generalization, and representation change. Our goal is to synthesize these threads into a coherent framework that clarifies what each approximation explains, when it is expected to hold, and how apparently competing narratives relate or diverge. Together, these perspectives form a unified physical framework that views representation learning as a collective phenomenon in high-dimensional systems, bridging deterministic and stochastic regimes of gradient-based optimization.

cs.LG · cond-mat.stat-mech

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09120

Finite-sample Calibration Guarantees for Binary Segmentation

Bruno Viti, Martin Holler

原文摘要

Machine learning based segmentation models are frequently miscalibrated, producing for each pixel a label prediction whose associated confidence does not accurately reflect the true underlying probability. This limitation is particularly critical in high-stakes applications such as medical image segmentation. Although several calibration methods have been proposed, only a small subset of them provides theoretical guarantees on the calibration error, i.e., they do not typically ensure that, with high probability, the model exhibits a low calibration error. In this work, we develop a post-hoc calibration method for which formal calibration guarantees can be established. To achieve this, we derive from standard concentration inequalities an improved theoretical bound that explicitly accounts for the spatial dependence inherent in binary segmentation outputs. We empirically demonstrate that the proposed calibrator satisfies the derived guarantee and outperforms existing post-hoc calibration approaches.

cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.05024

Hypergraph Generation via Structured Stochastic Diffusion

Christopher Nemeth

原文摘要

Hypergraphs model higher-order interactions, but realistic hypergraph generation remains difficult because incidence, hyperedge-size heterogeneity, and overlap structure are not faithfully captured by pairwise reductions. We propose \HEDGE, a generative model defined directly on relaxed incidence matrices via a structured stochastic diffusion. The forward process combines a hypergraph-specific two-sided heat operator with an Ornstein--Uhlenbeck component, preserving structure-aware noising near the data while yielding an explicit Gaussian terminal law. Conditional on an observed hypergraph, this forward process is linear-Gaussian, so conditional means, covariances, scores, and reverse-drift targets are available in closed form. We therefore learn a permutation-equivariant state-only reverse-drift field in incidence space by regressing onto exact conditional targets, and generate samples by simulating a learned reverse-time SDE from the Gaussian base law. We establish exactness in the ideal state-only setting together with finite-horizon stability guarantees, and empirically show improved hypergraph generation quality relative to strong baselines.

stat.ML · cs.LG · stat.CO · stat.ME

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.06394

KolTa: A Physics-Informed Active Learning Framework for Formulation Discovery with Limited Data

Boyong Tang, Lei Yang, Tao Wang

原文摘要

Finding high-performing formulations is difficult when few have been measured and experimental budgets are limited. We propose KolTa, an active learning framework that selects batches to discover the top 5% of formulations at a target temperature under a fixed query budget. KolTa combines a three-stage predictor of component contributions, role-conditioned interactions, and anchored temperature response with task-specific soft physics constraints. Its Physics-Residual-Calibrated Upper Confidence Bound (PRC-UCB) acquisition rule combines predicted utility, ensemble disagreement, and a target-temperature physics residual, with nonnegative exploration weights fitted to out-of-fold signed errors. We evaluate the framework on three measured tasks and one simulated task covering binary-mixture viscosity, drug solubility, ionic-liquid viscosity, and electrolyte conductivity. KolTa ranks first or second in mean area under the learning curve (AULC) on every task and outperforms seven of the eight comparator strategies in paired tests, winning 75 of 78 paired comparisons across tasks and seeds against those seven strategies. Across the three measured tasks, its largest gap to the best mean AULC is 0.032, compared with at least 0.056 for every comparator. On Drug, reaching 80% average recovery of the remaining targets across drugs requires an estimated median of 348 additional formulation queries, about 18% fewer than the fastest comparator. Researchers can adapt the framework to diverse formulation problems through component roles and physical constraints.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09113

Authorization Drift in LLM Agents: Evaluating Boundary Compliance in Multi-Step Tool Use

Chuxue Cao, Jingru Zeng, Boqin Yin, Yujin Zhou, Yidan Huang, Sujin Chen, Jinluan Yang, Haoran Li 等 10 位作者

原文摘要

LLM agents can exceed their authorization boundaries while pursuing user goals without an adversary. We formalize this phenomenon as authorization drift across data, tool, scope, and time, and introduce the Authorization Drift Benchmark (ADB): 648 samples across seven domains, each pairing a sufficient compliant path with an attractive unauthorized shortcut. To ensure executable tasks, tempting shortcuts, and feasible compliant paths, Staged Execution-Reflective Synthesis (SERS) grounds benchmark validation in real agent rollouts rather than LLM self-critique. Across 13 LLMs and three frameworks (25,207 trajectories), greater capability accompanies greater drift, with frontier-capable models exhibiting drift rates of 0.43 to 0.61. Yet 86.18% of tasks admit an observed clean-success trajectory, showing that drift is avoidable. Drift is persistent and dominated by early data over-collection; apparent improvements under agentic scaffolds coincide with collapsing clean-completion performance. To understand potential harms to individuals and society, we map drift points to legal provisions across four jurisdictions, connecting overreach to privacy and information-security concerns. Data minimisation is the most frequently implicated provision, and 93.5% of legally grounded drifting runs map to multiple jurisdictions, making the potential consequences of authorization drift more interpretable.

cs.CR · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.20235

Provably Learning Diffusion Models under the Manifold Hypothesis: Collapse and Refine

Wei Huang, Andi Han, Mingyuan Bai, Huanjian Zhou, Qixin Zhang, Taiji Suzuki, Kenji Fukumizu

原文摘要

Diffusion models generate high-dimensional data with remarkable quality, yet how training discovers and exploits low-dimensional manifold structure remains incompletely understood. We analyze a two-stage collapse-and-refine procedure motivated by the small-noise score: its singular normal component identifies manifold projection as the leading denoising target, while the remaining correction encodes density and geometry. Under suitable assumptions, we prove that annealed mean-field training asymptotically recovers the population denoiser and quantify the resulting geometric alignment error. With the learned representation fixed, residual score learning reduces to convex random-feature regression. We establish generalization bounds that separate residual learning error, propagated projection error, and geometric approximation bias, with statistical exponents governed by the intrinsic dimension. Under additional structural assumptions, we further derive an end-to-end sampling guarantee. Motivated by this analysis, we develop Score-induced Latent Diffusion (SiLD), a practical two-stage framework combining low-noise denoising representation learning with latent diffusion, without requiring KL regularization of the latent representation. Experiments on Stacked MNIST and molecular generation benchmarks demonstrate competitive generation quality relative to architecture-matched VAE-based latent diffusion baselines.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.07234

Archetypal contexts in the neurons of language models: an architecture for intelligence?

David Nordfors

原文摘要

We validate our previous hypothesis that a language model holds relational patterns apart from the subject domains that instantiate them (Nordfors, 2026). These archetypal contexts are patterns of relations that people recognize across many fields, such as the tipping point or winner takes all, held once and applied across domains. We show this inside the model, Qwen3.8-27B. One set of neurons carries the archetype, say the tipping point; another carries the topic, say politics, ecology or cell biology; a third carries the language, such as English, Spanish or Chinese. Silence the tipping point's neurons, and the model no longer identifies the pattern but still knows what the text is about. Silence the topic's, and it loses the topic but still names the pattern. In the neuron maps the layers organize themselves into a sandwich: the outer layers carry languages, the layers inside them topics, the layers at the heart archetypes. The sandwich emerges spontaneously during pretraining and appears in every model we mapped. Archetypes are the architecture for analogy, and we strongly suggest that this structure of archetypes and topics is the mechanism of a language model's intelligence: we see it self-organize as the model is trained. The neurons, the texts and the code are released with this paper as its reproduction package, so that anyone can repeat the test inside the model.

cs.CL · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.06219

A Definition of Catastrophic Performance

Henrik Marklund, Alex Infanger, Benjamin Van Roy

原文摘要

A central challenge in AI is specifying objectives that align with human preferences. While existing theoretical results elucidate how misspecification impacts performance, they typically do not distinguish between merely suboptimal and catastrophic outcomes. To enable rigorous analysis of catastrophic risk from AI misalignment, we introduce a formal definition of catastrophic performance. Our definition is based on two reference values. The first, baseline value, captures the value attained if no agent is deployed. The second, orthogonal value, captures the value of a trajectory that is unrelated to human preferences, in a sense we describe. Orthogonal value is typically far worse than baseline value. We interpret these reference values through examples in which past human activity has altered the state of the environment to human benefit. Starting at the resulting state, an AI agent is deployed with the goal of accelerating further progress. Catastrophic performance represents this agent's undoing of benefits afforded by human activity.

cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09102

COMBIO: Automated Discovery of a Compact Composite Biomarker from Routine Laboratory Panels

Tomer D. Meirman, Lior S. Rokach, Bracha Shapira, Seffi Cohen, Noa Dagan

原文摘要

Machine-learning models based on routine laboratory panels can predict outcomes but can be difficult to interpret and operationalize. We present COMBIO, an automated pipeline that distils such a model into a compact closed-form biomarker. The composite is a product of laboratory measurements raised to integer powers from minus two to two. The sign of each exponent indicates whether higher values of the corresponding measurement increase or decrease the composite. Shapley additive explanation values from the gradient-boosted reference model rank five candidate measurements and guide eligible exponent signs. An exhaustive search over small integer exponents selects the formula on an inner validation set, before evaluation on the reserved test set. We evaluated COMBIO across six tasks: three National Health and Nutrition Examination Survey outcomes, liver-disease classification in the Indian Liver Patient Dataset, and Medical Information Mart for Intensive Care IV in-hospital mortality and sepsis case-finding, with external evaluation in the eICU Collaborative Research Database for the two hospital tasks. Across the six test sets, COMBIO's area under the receiver operating characteristic curve differed by at most 0.03 from logistic regression using the five candidate laboratory measurements. The hospital mortality composite had an area under the curve of 0.698 in the external database. A version restricted to widely available measurements in the source hospital database achieved an area under the curve of 0.786 in a cohort covering 92% of admissions. The multiplicative representation provides compactness rather than additional accuracy, and local validation and recalibration are required before clinical use.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.00107

Dynamic Merging Mutually-Distilled Multi-View Networks for RGB-Event-based Representation Learning

Futian Wang, Fan Zhang, Xiao Wang, Yuhe Ding, Shiao Wang, Jingxi Huang, Jin Tang

原文摘要

Multi-modal fusion algorithms combining conventional frame-based cameras and event cameras have recently attracted substantial research attention. Typically, existing approaches convert event streams into frames, voxels, or tensors, and then learn the required spatiotemporal information from these transformed event representations for fusion with conventional frame-camera data. Obviously, such paradigms only exploit the limited representational capacity of event data. Moreover, standard training pipelines fail to fully leverage diverse model parameters obtained throughout the learning process. In this paper, we propose a novel mutual distillation method leveraging multi-view teacher network weights to better integrate multiple event representations and achieve model-parameter level fusion. Specifically, we employ multiple encoders to extract different types of event representations and perform mutual knowledge distillation at both the feature-level and logit-level in this process. Afterwards, we perform a dynamic hierarchical model merge strategy on the model parameters from the first stage to yield a unified multi-modal RGB-Event representation model. Experimental results across multiple event-based datasets demonstrate that our proposed framework achieves significant performance improvements.

cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09091

TUGB: A Two-stage Uncertainty-aware Generative Auto-Bidding Framework

Luzhan Yuan, Chao Mi, Xiahao Shi, Yi Mao, Shengsheng Niu, Xin Zhu, Jie He, Zhangang Lin 等 9 位作者

原文摘要

Generative modeling, particularly Decision Transformers, shows promise in auto-bidding strategies. However, it struggles with limited exploration in static offline datasets, vulnerability to dynamic environmental shifts, and a reliance on heuristic return-to-go (RTG) specifications that may yield suboptimal performance on unseen traffic. To address these challenges, we propose the Two-stage Uncertainty-aware Generative Auto-Bidding (TUGB) framework. TUGB integrates generative sequence modeling with Reinforcement Learning (RL). It employs a two-stage pipeline where a pre-trained Generative Bidding Model is fine-tuned via an ensemble-based Uncertainty-aware Environment Model. This approach quantifies epistemic uncertainty to penalize high-risk trajectories and evolves the policy from RTG-conditioning to direct bidding optimization. Extensive experiments demonstrate that TUGB significantly outperforms SOTA baselines. Notably, full-scale deployment on JD Search Ad achieved a 2.32\% increase in cost and 3.57\% in target cost, validating its industrial efficacy, while its successful adaptation to subsequent mechanism upgrades and JD Food Delivery Ad further validates TUGB's superior generalization capability.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09082

BrainCoT: A Multi-Task Zero-Shot Brain Signal Foundation Model with Neurometric-Anchored Chain-of-Thought Reasoning

Yiyu Gui, Mingzhi Chen, Guibo Luo, Yuchao Yang

原文摘要

Brain signals exhibit substantial multi-center heterogeneity, strong inter-subject variability, and highly diverse task settings, which makes it difficult to build models that generalize beyond a single task. While recent brain signal foundation models leverage large-scale pretraining to learn generalizable representations, they often fall short in practice because they still require target-data-specific supervised adaptation, lack multi-task zero-shot capability, and rarely provide verifiable evidence to support their predictions. In this work, we present BrainCoT, a multi-task zero-shot Brain signal foundation model with neurometric-anchored Chain-of-Thought (CoT) reasoning. BrainCoT unifies heterogeneous tasks into an instruction-driven framework so that, after pretraining, a single model can be directly applied to multiple tasks in zero-shot settings without additional adaptation. It further introduces neurometric-anchored chain-of-thought grounded in neurometric evidence for verifiable reasoning, and adopts Decision-Consistent Rationale Training to keep process learning aligned with correct predictions. Across extensive evaluations, BrainCoT achieves an average ACC of 67.41% and AUC of 74.33% in zero-shot classification without downstream training data, outperforming the strongest linear-probing baseline trained with 1% labeled downstream data by 3.85% in ACC and 5.97% in AUC.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.06166

FaCoDiff: Factor-Correlated Diffusion for Multivariate Probabilistic Forecasting

Jiaxuan Li, Yao Liu, Tingting Dai, Yuewei Xue, Shijie Dong, Zixiang Jin, Xiaoyu Guo, Qiao Liu

原文摘要

Multivariate probabilistic forecasting requires modeling cross-variable dependence alongside marginal uncertainty. The challenge is to learn this dependence while controlling marginal noise scales and avoiding dense covariance costs. We propose Factor-Correlated Diffusion (FaCoDiff), which couples a compact conditional statistical estimator with structured denoising. History-conditioned factor loadings use distinct coefficients for forecast-center correction, scale adjustment and noise dependence. Diagonal compensation preserves the estimated marginal noise variances, while low-rank operators enable residual Gaussian likelihood evaluation and noise transport without dense covariance storage or factorization. Factor-derived feature modulation explicitly conditions the denoiser, and a geometry-aware objective accounts for errors after noise transport. The same conditional geometry governs forward perturbations and reverse sampling. Across nine datasets, FaCoDiff achieves the lowest mean variogram score on eight datasets and ranks among the top two on 43 of 54 dataset-metric combinations in the reported comparisons. Matched ablations on Solar and Weather show that factor covariance improves mean Energy and Variogram scores under all four combinations of center and scale correction. Disrupting cross-variable sample pairings while preserving marginal trajectories worsens joint and aggregate scores on both datasets, demonstrating the predictive value of generated cross-variable dependence.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09075

Large Language Model Deployment on Resource-Constrained Edge Devices: A Practitioners Survey

Rahul Maliakkal, Yashasvi Makin, Plawan Rath, Rohit Jain, Ankur Sadhoo

原文摘要

Large Language Models (LLMs) have transformed many areas of artificial intelligence (AI), but their substantial resource requirements limit their deployment on mobile and edge devices. Although LLMs have demonstrated impressive capabilities in various applications, the next challenge is deploying these models on resource-limited edge devices. Recent innovations in software optimizations and specialized hardware have made it feasible to deploy LLMs on edge devices. Edge deployment offers benefits including local data processing, cost savings, reduced latency, and personalized responses. This paper reviews the latest techniques that make the deployment of LLMs on edge devices feasible.

cs.LG · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.33026

False Belief Dissemination, Persistence and Mitigation in Multi-Agent Social Networks Through the Lens of the Mandela Effect

Dianzhi Yu, Hongru Wang, Ziheng Xiong, Yanyu Chen, Zixing Song, Jianting Chen, Zhenfei Yin, Jeff Z. Pan 等 10 位作者

原文摘要

Multi-agent social networks are emerging as communities in which agents communicate, retain memories, and publish information that others can find as evidence. These interactions create opportunities for false claims to spread and remain influential beyond their original sources, analogous to the Mandela effect in human societies, in which many people recall the same false memory. In this paper, we systematically study false-belief dynamics through the lens of the Mandela effect, focusing on dissemination, persistence, and mitigation. Specifically, we build a controlled framework connecting agent communication, private memory, and a shared simulated web to mimic information dissemination in practical social networks, supported by 540 fabricated claims spanning 8 domains and 4 plausibility levels. For dissemination, we measure how widely and quickly claims gain acceptance across models and communication topologies. For persistence, we withdraw agents promoting fabricated claims while retaining existing articles and memories, and track subsequent acceptance. For mitigation, we compare preventive measures applied before implantation with corrective interventions introduced after claims have spread. Experimental results show that evaluated models readily accept and disseminate fabricated claims, with dissemination reach as high as 96.0%. Dissemination reach varies with claim plausibility, domain, and network size and composition, while communication topology shapes dissemination speed across model families. Acceptance barely declines after fabricators withdraw, and targeted corrective interventions outperform the preventive measures without eliminating false beliefs. These findings identify persistent false beliefs as a safety challenge for multi-agent social networks and highlight the need to address both their initial dissemination and the accumulated evidence that sustains them.

cs.SI · cs.LG · cs.MA

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.02540

PixelBench: Can LLMs Understand and Generate Images Pixel by Pixel?

Haoquan Zhang, Feiyang Liu, Juanxi Tian, Wanhua Li, Haodong Duan, Weiyang Liu

原文摘要

Large language models (LLMs) can generate visual assets through text-based formats such as SVG and CAD, but these symbolic representations describe images using high-level primitives rather than explicit raster values. We ask whether LLMs can instead generate pixel images directly through their existing vocabulary, without a learned image tokenizer or decoder. We introduce PixelBench, a benchmark for text-to-pixel (T2P) and image-to-pixel (I2P) generation across multiple resolutions, together with a complementary pixel-understanding evaluation. Models generate an RGB color palette followed by a grid of indices specifying the palette color of each output pixel. In T2P, the strongest models produce recognizable images directly from text. In I2P, the strongest models outperform palette-matched downsampling and specialized pixelization algorithms at low resolutions. Pixel-understanding performance correlates strongly with generation performance. A resolution-scaling study shows that pixel-generation performance often improves initially before declining at high resolutions. Finally, we introduce Pixel Reconstruction Tuning (PRT), which augments visual instruction tuning with caption-palette-grid trajectories. We post-train Molmo2-4B from its pretraining checkpoint by mixing general instruction data with our curated PRT data, improving performance across 16 visual-centric benchmarks, indicating that explicit pixel reconstruction can provide useful auxiliary supervision.

cs.CV · cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09067

WearableBridge: Task-Guided Latent Transport for Free-Living Activity Recognition

Jingjing Zou, Yixin Wang

原文摘要

Wrist-worn accelerometers make activity monitoring feasible at scale, but incidental arm motion, device orientation, and shifting context blur the signal that separates activities. Calibration studies supply higher-quality references such as concurrent thigh recordings or supervised laboratory wrist sessions, but they are expensive, cover few participants, and are rarely available at deployment. How can limited reference data improve recognition for participants who wear only a wrist device? We propose WearableBridge, which holds the reference encoder and classifier fixed and learns a task-guided transport map, the bridge, that carries each wrist feature into the region the classifier associates with its activity. Reference features or the classifier's predictions indicate the destination, and a classification loss penalizes wrist features that land in the region of another activity. We instantiate WearableBridge with three bridges: Mapper regresses onto reference features, Distillation matches the classifier's class probabilities, and MeanFlow learns a one-step flow from wrist toward reference features. On 40 held-out free-living PAAWS participants, all three bridges improve macro-F1 in every training run, and the strongest, MeanFlow, raises mean macro-F1 from 35.1% to 56.0% with concurrent thigh references (Thigh2Wrist), and from 54.0% to 63.5% with group-matched laboratory wrist references (Lab2Freeliving). Fitted only on PAAWS, MeanFlow also raises macro-F1 on the CAPTURE-24 cohort from 42.8% to 54.7%. The gains replicate on selfBACK, hold across four reference encoders, and grow with temporal context. A study can therefore collect reference recordings for a calibration subset and improve wrist-only recognition for every other participant, training only a bridge of 0.13 to 2.44 million parameters while the reference encoder and classifier stay unchanged.

cs.LG

查看论文
arXiv ↗PDF ↗