跳到正文
研踪PaperTrail

版本更新

查看已发布论文的最新修订,在详情页对照实际观测到的版本。

部分采集异常

全站更新概况

+1084新增论文
+883其中 AI 相关
+130已有论文修订
+92新增 AI 导读

arXiv 最近完成扫描:2026-11-18 04:28 · 全站最近入库:2026-11-18 19:45各信源进度 →

统计口径与数据新鲜度

统计 2026-11-18 01:27 — 2026-11-19 01:27(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:2026-11-18 04:28最近发现新增版本:2026-11-18 19:45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。

26,870 已收录论文22,374 AI 相关8,156 有修订112 HF 社区发现

论文修订列表

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 8,156 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-18 04:27(北京时间)
版本更新 · v3arXiv:2605.13230

Teacher-Guided Policy Optimization for On-Policy Reasoning Distillation under Large Policy Divergence

Xinyu Liu, Kechen Jiao, Chunyang Xiao, Runsong Zhao, Junhao Ruan, Bei Li, Jiahao Liu, Qifan Wang 等 13 位作者

原文摘要

On-policy distillation (OPD) has become a promising paradigm for reasoning-oriented post-training of large language models (LLMs), especially when combined with reinforcement learning from verifiable rewards (RLVR). Existing OPD methods rely on reverse KL (RKL)-based teacher supervision over trajectories sampled from the student policy. However, we identify a critical limitation: under large teacher--student policy divergence, RL-driven exploration often produces trajectories outside the teacher distribution, resulting in uninformative negative feedback. To address this, we propose Teacher-Guided Policy Optimization (TGPO), an on-policy reasoning distillation method that remains effective under large policy divergence settings. Rather than relying solely on evaluative supervision, TGPO uses teacher to directly guide token level generation conditioning on student-generated contexts; together with RLVR-style trajectory level rewards, TGPO steers exploration toward improved continuations. Experiments on reasoning benchmarks show that TGPO consistently outperforms existing RKL-based OPD methods and remains robust across different teacher models.

cs.LG · cs.AI

版本更新 · v2arXiv:2611.04072

Finite-Sample Convergence in Networked Average Reward MARL: Decentralization Pitfalls and Entropy Remedies

Yizhou Zhang, Yashaswini Murthy, Laixi Shi, Adam Wierman

原文摘要

We study the problem of average reward Multi-Agent Reinforcement Learning (MARL) where agents interact within a network. Each agent in the network conducts local updates with information within its $k$-hop neighborhood and collaboratively maximizes the overall reward of the entire network. We first provide impossibility results in achieving convergence to the global optimal joint policies in our setting. These impossibility results highlight the challenges of decentralized learning with local information in multi-agent systems, namely the issues of multiagency, where each agent independently optimizes its policy, and partial observability, where agents have limited visibility into the global state. Given these challenges which indicate that decentralized policy optimization can generally be certified only up to stationarity, we provide finite-sample convergence guarantees for a decentralized actor-critic algorithm with linear function approximation that converges to an approximate stationary point with small gradient norm. To overcome such impossibility results, we further show that adding fixed-state entropy regularization reshapes the objective landscape which leads to even stronger global convergence guarantees for our proposed actor-critic algorithm.

cs.LG · cs.MA

版本更新 · v3arXiv:2602.04042

Partition Tree: Conditional Density Estimation over General Outcome Spaces

Felipe Angelim, Alessandro Leite

原文摘要

We propose Partition Tree, a tree-based framework for conditional density estimation over general outcome spaces that supports both continuous and categorical variables within a unified formulation. Our approach models conditional distributions as piecewise-constant densities on data-adaptive partitions and learns trees by greedily minimizing a surrogate for conditional log-loss. This yields a scalable alternative to existing probabilistic trees that does not make parametric assumptions about the target distribution. We further introduce Partition Forest, an ensemble extension obtained by averaging conditional densities. Empirically, we demonstrate improved probabilistic prediction over CART-style trees and competitive performance compared to state-of-the-art probabilistic tree methods and Random Forests.

cs.LG · stat.ME · stat.ML

版本更新 · v2arXiv:2605.04266

Explaining and Preventing Alignment Collapse in Iterative RLHF

Etienne Gauthier, Francis Bach, Michael I. Jordan

原文摘要

Reinforcement learning from human feedback (RLHF) typically assumes a static or non-strategic reward model (RM). In iterative deployment, however, the policy generates the data on which the RM is retrained, creating a feedback loop. Building on the Stackelberg game formulation of this interaction, we derive an analytical decomposition of the policy's true optimization gradient into a standard policy gradient and a parameter-steering term that captures the policy's influence on the RM's future parameters. We show that standard iterative RLHF, which drops this steering term entirely, suffers from alignment collapse: the policy systematically exploits the RM's blind spots, producing low-quality, high-reward outputs whose feedback reinforces the very errors it exploits. To mitigate this, we propose foresighted policy optimization (FPO), a mechanism-design intervention that restores the missing steering term by regularizing the policy's parameter-steering effect on RM updates. We instantiate FPO via a scalable first-order approximation and demonstrate that it prevents alignment collapse on both controlled environments and an LLM alignment pipeline using Llama-3.2-1B.

cs.LG · stat.ML

版本更新 · v4arXiv:2510.16420

Exact Quantum Circuit Optimization is co-NQP-hard

Adam Husted Kjelstrøm, Andreas Pavlogiannis, Jaco van de Pol

原文摘要

As quantum computing resources remain scarce and error rates high, minimizing the resource consumption of quantum circuits is essential for achieving practical quantum advantage. Here we consider the natural problem of, given a circuit $C$, computing a circuit $C'$ that behaves equivalently on a desired subspace, and that minimizes a quantum resource type, expressed as the count or depth of (i) all gates, or (ii) non-Clifford gates, or (iii) superposition gates, or (iv) entanglement gates. We show that, when $C$ is expressed over any gate-set that can implement the H and TOF gates exactly, a standard property of approximately universal gate-sets, each of the above optimization problems is hard for co-NQP, and hence outside the Polynomial Hierarchy, unless the Polynomial Hierarchy collapses. This complements a recent result of Van de Wetering and Amy (arXiv, 2023) which establishes an NP-hardness lower bound when equivalence is over the full state space, and tightens the gap to the corresponding $\text{NP}^\text{NQP}$ upper bound known for cases (i)-(iii) over Clifford+T and (i)-(iv) over H+TOF circuits. Our result also generalizes a result by Tanaka (Int. J. Quantum Inf., 2010) to other gate-sets and quantum resources.

quant-ph · cs.CC

版本更新 · v2arXiv:2605.14972

Viverra: Text-to-Code with Guarantees

Haoze Wu, Rocky Klopfenstein, Keith Farkas, Nina Narodytska

原文摘要

A fundamental limitation of Text-to-Code is that no guarantee can be obtained about the correctness of the generated code. Therefore, to ensure its correctness, the generated code still has to be reviewed, tested, and maintained by developers. However, parsing through LLM-generated code can be tedious and time-consuming, potentially negating the productivity gains promised by AI-coding tools. To address this challenge, we present Viverra, a system that automatically produces formally verified annotations alongside generated code to aid user's understanding of the generated program. Given a natural-language task description, Viverra prompts an LLM to synthesize a C program together with candidate assertions expressing safety and correctness properties. It then verifies those assertions in a compositional and best-effort manner via a portfolio of bounded model checkers. Evaluation on 17 diverse programming tasks suggests that Viverra can efficiently generate code with verified assertions, and that these assertions improve users' performance on code-comprehension tasks in a user study with more than 400 task completions.

cs.SE · cs.AI · cs.HC · cs.LO

版本更新 · v2arXiv:2605.27946

Is Backpropagation Optimal? When Synthetic Gradients Improve Sample Efficiency

Yibo Jacky Zhang, Zeyu Tang, Sanmi Koyejo

原文摘要

Backpropagation is the default learning rule for artificial neural networks and is often treated as the settled approach whenever differentiability is available. In this work, we revisit this convention through a theoretical lens of sample efficiency. We introduce a unified vectorized feedback framework for loss-based and reward-based learning on computational graphs, in which synthetic gradients emerge as a natural alternative to backpropagation. We characterize the conditions under which synthetic gradients can achieve a lower gradient-estimation mean squared error than backpropagation. We construct examples illustrating that this sample efficiency advantage can be arbitrarily large. Experiments on contextual bandits and reinforcement learning tasks demonstrate the potential of our theoretical findings.

stat.ML · cs.LG

版本更新 · v3arXiv:2609.28870

When Fancy Eviction Fails: Rethinking Cache Replacement For LLM Prefix Reuse

Yiyu Liu, Minlan Yu, Juncheng Yang

原文摘要

Long-running LLM applications and autonomous agents repeatedly send growing context, making prefix caching critical for reducing prefill cost. This raises a fundamental question: do decades of traditional cache-management techniques transfer directly to agentic and conversational LLM serving? We analyze production traces comprising over 20 billion processed tokens and evaluate 14 eviction algorithms across capacity-constrained HBM and large memory-pool settings. We find that simple Least Recently Used (LRU) is surprisingly robust, offering competitive performance against sophisticated traditional policies, though substantial headroom to Belady's optimum remains. The reason is structural: prefix reuse is dominated by the steady pacing of active sessions, making recency an unusually strong predictor for eviction. Nevertheless, prefix caching diverges from traditional workloads in ways that recency ignores, notably the prevalence of single-turn requests, extreme session footprint skew, and highly non-uniform miss costs because attention computation scales with token depth. To close the gap to optimality, we establish several design principles for prefix-cache management: keeping recency as the baseline while incorporating quick demotion to filter one-hit prompts, compute-aware eviction to prioritize expensive misses, and capacity-adaptive eviction granularity. Our traces and simulator are publicly available.

cs.DC · cs.LG

版本更新 · v3arXiv:2507.12412

Contrastive Nonmyopic Objective Cost-Tradeoff Acquisition for Longitudinal Data

Dzung Dinh, Boqi Chen, Yunni Qu, Marc Niethammer, Junier Oliva

原文摘要

In many critical domains, features are not freely available at inference time: each measurement may come with a cost of time, money, and risk. Longitudinal prediction further complicates this setting because both features and labels evolve over time, and measurements missed at earlier timepoints may become permanently unavailable. We propose CAPE (Contrastive Acquisition-Plan Embeddings), a partitioning acquisition policy for longitudinal active feature acquisition. CAPE first defines NOCT, an oracle-based objective that scores a set of future feature-time acquisitions by its expected predictive loss together with its acquisition cost. Based on NOCT, CAPE learns a contrastive acquisition-utility manifold of masked partial observations, where proximity reflects the expected utility of future acquisitions. Offline, training states are embedded and partitioned at each rollout timepoint; candidate future plans are scored within each partition using plug-in NOCT, and the best partition-level acquisition plans are cached. During inference, CAPE retrieves the cached plan via nearest-centroid lookup, enabling low-latency adaptive acquisitions. Experiments on synthetic and real-world healthcare datasets demonstrate that CAPE outperforms nonparametric, greedy, and RL-based alternatives, achieving higher accuracy at lower acquisition costs. Code is publicly available at https://github.com/dzungdinhh/CAPE.

cs.LG · cs.AI

版本更新 · v2arXiv:2611.04825

UniFlow: Unified Multi-Scale Flow Matching for Time Series Generation

Shibo Feng, Wei Li, Songhua Liu, Min Wu, Chunyan Miao, Peilin Zhao

原文摘要

Real-world time series exhibit complex dynamics across multiple temporal resolutions, yet effectively incorporating multi-scale information into generative modeling remains challenging without increasing generative complexity. We propose UniFlow, a unified framework that integrates multi-scale representation learning with efficient non-autoregressive generation through a shared-semantic discrete interface. Specifically, a multi-scale tokenizer employs shared-index voting to consolidate complementary temporal information into a single public-ID sequence, while scale-specific codebooks preserve the information required for reconstruction. Building on this unified representation, we develop geometry-aware categorical flow matching, which initializes transport from learned low-rank anchors and generates public identities non-autoregressively. This design captures multi-scale temporal structure without requiring multiple generative token streams or sequential token decoding. Experiments across four benchmarks and both short- and long-term settings demonstrate improved generative fidelity, strong cross-scale consistency, and substantial inference speedups over representative autoregressive and diffusion-based baselines. Code is available at https://github.com/kkking-kk/UniFlow

stat.ML · cs.AI

版本更新 · v3arXiv:2608.14689

A Reproducibility Study of Partial Residual Ablations in Pre-LN Transformers

Pratikkumar Babariya

原文摘要

Residual connections are a fundamental component of transformer architectures, yet the roles of the attention and feed-forward residual pathways remain poorly understood when considered independently. This paper presents a reproducibility study of partial residual ablations in Pre-LN GPT-style transformers trained at two scales (10M and 124M parameters). I compare four architectural configurations by selectively removing the attention residual connection, the feed-forward residual connection, or both. At 10M scale, a controlled 8-seed deterministic sweep shows a clear asymmetry: removing the attention residual (FFNOnly) reaches the No-Residual collapse regime (3.350 +/- 0.002), whereas removing the feed-forward residual (AttnOnly) remains well separated from it (1.580 +/- 0.003). A subsequent controlled 124M sweep establishes that the direction of this asymmetry persists under matched seeds: across five seeds each, AttnOnly reaches 6.037 +/- 0.355 versus 7.569 +/- 0.001 for FFNOnly, with no overlap between the observed ranges. AttnOnly nevertheless remains substantially degraded relative to FullResidual (4.577 +/- 0.012) and exhibits markedly greater seed sensitivity at 124M. During the investigation, I identified and corrected an experimental measurement confound in runtime gain scaling and retained an intermediate reproduction failure rather than excluding it. I propose cross-position routing through self-attention as a falsifiable hypothesis for the observed asymmetry; no clean causal test of this mechanism has yet been completed. To support reproducibility, I release the source code, experiment configurations, training logs, and experimental results, including intermediate non-reproducing runs.

cs.LG

版本更新 · v2arXiv:2605.17510

Scale-Dependent Collective Adaptation in Self-Amending LLM Societies: A Cross-Family Study of Emergent Governance

Kazuya Horibe, Masaomi Hatakeyama, Gen Masumoto, Takashi Hashimoto, Peter Romero

原文摘要

We study group decision-making in artificial societies where the rules of play are themselves subject to collective amendment. Using the self-amending game Nomic, we compare multiple scales across two LLM families and find that collective adaptation does not improve monotonically with model size. Instead, both families exhibit a narrow mid-scale regime that supports sustained rule adoption, diverse amendments, and balanced consensus. Smaller models tend to remain rule-inert, whereas larger models often converge on restrictive voting patterns, and heterogeneous mixed-size groups collapse into veto-driven gridlock. These cross-scale contrasts persist under temperature perturbations and under a shift from unanimity to majority voting, although latent-state structure varies by family and scale. Hidden-state divergence alone does not explain collective performance: high representational divergence can coincide with poor behavioural outcomes. Linear probes reveal regime-selective coupling between latent vote-predictive signals and collective behaviour, but decodability is necessary rather than sufficient for adaptive play. Overall, the recurring regularity is non-monotonicity, not the particular scale at which the optimum appears. Self-amending games therefore provide a controlled testbed for studying collective adaptation in artificial societies beyond raw model scale.

nlin.AO · cs.MA

版本更新 · v3arXiv:2603.24511

Claudini: Autoresearch Discovers State-of-the-Art Adversarial Attack Algorithms for LLMs

Alexander Panfilov, Peter Romov, Igor Shilov, Yves-Alexandre de Montjoye, Jonas Geiping, Maksym Andriushchenko

原文摘要

We show that AI agents are capable of discovering novel algorithms for adversarial attacks against LLMs, advancing the state of the art on white-box jailbreaking and prompt injection evaluations. We deploy frontier agents, such as Claude Code and Codex, in an autoresearch loop with access to a library of 30+ prior methods and an evaluation script with a fixed compute budget. We show this pipeline to be effective in jailbreaking OpenAI's GPT-OSS-Safeguard-20B and in prompt injections against Meta-SecAlign-70B, an adversarially robust model. For GPT-OSS-Safeguard, the best agent-discovered method achieves up to 80\% attack success rate on CBRN queries, compared to <50\% for existing methods. For SecAlign, it achieves 100\% ASR, while the best prior automated methods only achieve 82\%. Notably, in our setting, attack methods are developed on unrelated surrogate models for a pure random-target token-forcing task, yet generalize directly to prompt injection on the adversarially trained model. Finally, we trace the lineage of methods developed during autoresearch, characterizing the agents' strategies and failure modes. Adversarial ML has long held that defenses must be evaluated against attacks tailored to them; autoresearch automates this principle, and we argue it should be the minimum bar for defense evaluation going forward.

cs.LG · cs.AI · cs.CR

版本更新 · v5arXiv:2602.00387

Singular Bayesian Neural Networks

Mame Diarra Toure, David A. Stephens

原文摘要

Bayesian neural networks promise calibrated uncertainty but require $O(mn)$ parameters for standard mean-field Gaussian posteriors. We argue this cost is often unnecessary, particularly when weight matrices exhibit fast singular value decay. By parameterizing weights as $W = AB^{\top}$ with $A \in \mathbb{R}^{m \times r}$, $B \in \mathbb{R}^{n \times r}$, we induce a posterior that is \emph{singular} with respect to the Lebesgue measure, concentrating on the rank-$r$ manifold. This singularity captures structured weight correlations through shared latent factors, geometrically distinct from mean-field's independence assumption. We derive PAC-Bayes generalization bounds whose complexity term scales as $\sqrt{r(m+n)}$ instead of $\sqrt{m n}$, and prove loss bounds that decompose the error into optimization and rank-induced bias using the Eckart-Young-Mirsky theorem. We further adapt recent Gaussian complexity bounds for low-rank deterministic networks to Bayesian predictive means. Empirically, across MLPs, LSTMs, and Transformers on standard benchmarks, our method achieves competitive predictive performance while using up to $33\times$ fewer parameters than 5-member Deep Ensembles. It substantially improves OOD detection and often improves calibration relative to mean-field and perturbation baselines, while Deep Ensembles can still be stronger on in-distribution likelihood-based metrics.

stat.ML · cs.LG · stat.AP

版本更新 · v5arXiv:2602.14697

Evolutionary System Prompt Learning for Reinforcement Learning in LLMs

Lunjun Zhang, Ryan Chen, Bradly C. Stadie

原文摘要

Building agentic systems that can autonomously self-improve from experience is a longstanding goal of AI. Large language models (LLMs) today primarily self-improve via two mechanisms: self-reflection for context updates, and reinforcement learning (RL) for weight updates. In this work, we propose Evolutionary System Prompt Learning (E-SPL), a method for jointly improving a model's experiential context and its weights. In each RL iteration, E-SPL samples trajectories under multiple system prompts in parallel, then uses them to jointly update the weights with RL and evolve the system prompts with self-reflection. E-SPL encourages a natural division between procedural knowledge in weights and interpretable declarative knowledge in system prompts. Most notably, in an easy-to-hard generalization setting (AIME $\rightarrow$ BeyondAIME), E-SPL improves RL success rate from 38.8% $\rightarrow$ 45.1%. E-SPL also improves RL on AIME 2025 (56.3% $\rightarrow$ 60.6%), HMMT 2025 (50.0% $\rightarrow$ 52.7%), and agentic search (44.2% $\rightarrow$ 48.6% on gpt-oss-120b). Across all settings, E-SPL outperforms both RL-only and evolution-only baselines, demonstrating that weight updates and context updates are deeply synergistic and can together yield gains in generalization that neither achieves alone. Code is available at https://github.com/LunjunZhang/E-SPL.

cs.AI · cs.LG

版本更新 · v2arXiv:2605.07020

FlashMol: High-Quality Molecule Generation in as Few as Four Steps

Xinyuan Wei, Zian Li, Shaoheng Yan, Cai Zhou, Muhan Zhang

原文摘要

Generating chemically valid 3D molecular conformations is critical for computational drug discovery. Classical diffusion-based models like GeoLDM perform well but require hundreds of steps, making large-scale in silico screening impractical. Recent efforts on few-step molecular generation have accelerated this process to 12-50 steps, but they often largely sacrifice sample stability. In this work, we present FlashMol, an ultra-fast molecule generative model producing high-quality molecular conformations in as few as 4 steps. To achieve this, we adapt distribution matching distillation (DMD) -- a reverse KL-divergence minimization objective -- to the molecular domain for effective distillation. Considering the local minimization behavior of DMD, we respace the molecule generation timesteps, providing the generator with much better initialization and enables effective distillation. Additionally, to mitigate the mode-seeking behavior of DMD and improve diversity, we further regularize it with a Jensen-Shannon divergence term, which incorporates the mean-seeking behavior of the forward KL divergence. Extensive experiments on QM9 and GEOM-DRUG datasets demonstrate that FlashMol matches and even surpasses the original 1000-step teacher: by applying respacing to the GeoLDM teacher (GeoLDM-respaced), we achieve comparable results to the 1000-NFE teacher with as few as 16 NFEs. After further distillation, FlashMol is able to sample with only 4 NFEs while maintaining high molecular quality, achieving up to 250$\times$ acceleration compared to the GeoLDM teacher.

cs.LG · cs.AI

版本更新 · v2arXiv:2510.02181

EvolveCaptions: Empowering DHH Users Through Real-Time Collaborative Captioning

Liang-Yuan Wu, Dhruv Jain

原文摘要

Automatic Speech Recognition (ASR) systems often struggle to accurately transcribe speech from Deaf and Hard of Hearing (DHH) speakers. Existing personalization approaches typically require substantial pre-recorded datasets and burden DHH users. We present EvolveCaptions, a collaborative, error-driven personalization system that connects caption correction with speaker-specific ASR adaptation. When transcribing a DHH speaker's speech, hearing partners repair transcription errors, and the system generates short, targeted clauses for the DHH speaker to record. These samples are used to incrementally fine-tune the model. In a study with 12 DHH and six hearing participants, EvolveCaptions reduced Word Error Rate (WER) across five scripted reading rounds, requiring an average of five minutes of additional speech recording. Participants found the interfaces usable but considered recording and correction effortful; acceptability depended on context and anticipated long-term benefit. These findings show the potential of collaborative, cumulative adaptation while exposing the labor and conditions needed to sustain it.

cs.HC · cs.AI · cs.SD · eess.AS

版本更新 · v2arXiv:2605.13810

DASHQuant: Provable Quantization with a Single Randomized Hadamard Transform

Ying Feng, Piotr Indyk, Michael Kapralov, Dmitry Krachun, Boris Prokhorov

原文摘要

Vector quantization via random projection followed by scalar quantization is a fundamental primitive in machine learning, with applications ranging from similarity search to federated learning and KV cache compression. While dense random rotations yield clean theoretical guarantees, they require $Θ(d^2)$ time. The randomized Hadamard transform $HD$ reduces this cost to $O(d \log d)$, but its discrete structure complicates analysis and leads to weaker or purely empirical compression guarantees. In this work, we introduce DASHQuant (Dithered Accelerated Single-Hadamard Quantization), a provable variant of this approach. Specifically, the quantizer applies $HD$ to the input vector and adds a random dithering before quantizing, injecting additional randomness at negligible cost. We prove that this approach is unbiased and provides mean squared error bounds that asymptotically match those achievable with truly random rotation matrices. In particular, we prove that a dithered version of TurboQuant, and a special case of EDEN, achieves mean squared error $\bigl(π\sqrt{3}/2 + o(1)\bigr) \cdot 4^{-b}$ at $b$ bits per coordinate, where the $o(1)$ term vanishes uniformly over all unit vectors and all dimensions as the number of quantization levels grows.

cs.LG · cs.DS

版本更新 · v3arXiv:2604.09787

Learning What's Real: Disentangling Signal and Measurement Artifacts in Multi-Sensor Data, with Applications to Astrophysics

Pablo Mercader-Perez, Carolina Cuesta-Lazaro, Daniel Muthukrishna, Jeroen Audenaert, V. Ashley Villar, David W. Hogg, Marc Huertas-Company, William T. Freeman

原文摘要

Data collected from the physical world is always a combination of multiple sources: an underlying signal from the physical process of interest and a signal from measurement-dependent artifacts from the sensor or instrument. This secondary signal acts as a confounding factor, limiting our ability to extract information about the physics underlying the phenomena we observe. Furthermore, it complicates the combination of observations in heterogeneous or multi-instrument settings. We propose a deep learning framework that leverages overlapping observations, a dual-encoder architecture, and a counterfactual generation objective to disentangle these factors of variation. The resulting representations explicitly separate intrinsic signals from sensor-specific distortions and noise, and can be used for counterfactual view generation, parameter inference unconfounded by measurement distortions, and instrument-independent similarity search. We demonstrate the effectiveness of our approach on astrophysical galaxy images from the DESI Legacy Imaging Survey (Legacy) and the Hyper Suprime-Cam (HSC) Survey as a representative multi-instrument setting. This framework provides a general recipe for scientific and multi-modal self-supervised pretraining: construct training pairs from overlapping observations of the same physical system, treat sensor- or modality-specific effects as augmentations, and learn invariant representations through counterfactual generation.

astro-ph.IM · astro-ph.GA · cs.LG

版本更新 · v2arXiv:2610.01002

What Can Analogy Tell Us About Artificial Consciousness?

Keith J. Holyoak, Martin M. Monti

原文摘要

Who or what is conscious? Because subjective experience is directly accessible only in the first person, judgments about consciousness in other entities depend partly on analogy. Historically, such inferences have focused on nonhuman animals, but advances in artificial intelligence have raised the possibility of conscious AI. Here we develop a causal framework for evaluating such evidential analogies. The key distinction is between similarities in factors plausibly involved in generating consciousness and similarities in downstream behavioural or cognitive effects. Our framework weights source-target similarity by causal relevance while allowing for unknown causes, disabling differences and alternative routes to consciousness. Applied to biological systems, it explains why analogical support generally weakens with increasing causal distance from humans. Applied to contemporary AI, it suggests that behavioural similarity provides only limited evidence for consciousness because relevant causal correspondences remain poorly established. The framework also clarifies what evidence would strengthen claims of artificial consciousness.

cs.AI

版本更新 · v2arXiv:2609.07868

SGD in Multiclass Logistic Regression: Sequential Learning and Scaling Laws

Konstantinos Christopher Tsiolis, Denny Wu, Christos Thrampoulidis, Murat A. Erdogdu

原文摘要

We study the training dynamics of multiclass logistic regression on high-dimensional mixture models with a large number of classes and establish precise scaling laws governing the cross-entropy risk under gradient-based optimization. We show that learning proceeds sequentially across classes, from most to least frequent. When the class priors follow a power law distribution, the risk dynamics decompose into three phases: an initial plateau until the first class is learned, a power-law decay regime during which sequential learning occurs, and a final convergence regime. We then analyze how model capacity interacts with optimization under a fixed compute budget. When the effective dimension is restricted via projection onto leading principal components, the risk decomposes into a capacity term (a power law in the retained dimension) and an optimization term (a power law in training time). Optimizing this tradeoff yields a compute-optimal scaling law for logistic regression, with explicit prescriptions for model size and training time as functions of compute. These results extend theoretical scaling laws from linear regression to multiclass classification, while connecting to empirical scaling laws observed in large-scale neural networks.

stat.ML · cs.LG

版本更新 · v3arXiv:2604.16706

Measuring What Tool-Using LLM Agents Actually Do: Structured Validation, Causal Error Propagation, and Fabricated Tool Use

Bhaskar Gurram

原文摘要

Tool-using agents built on large language models (LLMs) are usually scored by comparing the final answer with a reference text, using a string heuristic or an LLM judge. This is unreliable when the references describe the task rather than its answer. We replace it with a deterministic validator that checks the tools called, the executed parameters, the resulting state, and whether the values in the answer are supported by the correct tool observations. We re-scored 33,583 traces from 13 agents on simulated calendar, weather, medical and retail tools. The simulator reproduced all 10,396 logged observations, and the gold observations supported the validator in 16 of 18 disagreements with a three-annotator majority (the annotators in none). The instrument changes conclusions: on the same 306 traces, Gemini-2.0-Flash scores 63.4% under the substring heuristic and 5.6% under the validator. In a paired design (same task and model, with and without one schema-valid wrong argument injected into the first tool call), the error rate rises from 52.4% to 74.5% (+22.0 percentage points, 95% CI 18.4-25.5; 1,085 pairs, 7 models), and by 44.7 points (38.4-51.0) where the corrupted call executed without errors. An LLM-judge ensemble estimates +2.5 points on the same pairs. Agents also report tool results without executing any call, in 0-42.5% of traces depending on the model (rule-based lower bounds), largely because the harness accepts an action and a final answer in one completion. A rule-based runtime monitor costs about 7 microseconds per trace but reduces wrong answers mainly by abstaining.

cs.AI · cs.CL · cs.MA

版本更新 · v3arXiv:2606.30901

GRAPE: Graph-Augmented Prototype Explanations for Interactive Medical Image Diagnosis

Rasul Khanbayov, Erchin Serpedin, Hasan Kurban

原文摘要

Prototype-based medical image classifiers present three clinical limitations: they treat findings as independent, silently amplify unsafe physician feedback, and require full retraining whenever a new finding is needed. We present GRAPE (Graph-Augmented Prototype Explanations), a unified architecture that targets all three challenges. First, a Graph Attention Task Head boosts macro-F1 by +13.8,pp over the prototype baseline on TBX11K but not on NIH ChestX-ray14, with no graph-specific benefit established. Second, a Concept-Mismatch Safety Check, to our knowledge the first such mechanism in prototype-based medical classifiers, warns when the model's dominant finding inside a doctor-drawn region conflicts with the claimed label, catching 85% of simulated erroneous annotations with no extra inference cost at a favorable operating point, though sensitivity falls substantially at clinically realistic false-positive budgets. Third, Open-Vocabulary Prototype Anchoring aligns visual prototypes to clinical text, allowing a new finding to be added from a single labeled image without modifying any other component, evaluated for localization only. On NIH ChestX-ray14, one Effusion example matched that concept's low fully-supervised Pointing Game ceiling in one run but not in a second. On TBX11K, prototype maps achieve 2.1x better lesion localization than end-to-end concept-based baselines. The graph head adds only +1~ms latency at interactive batch size. The project page is available at https://kurbanintelligencelab.github.io/GRAPE.

cs.CV

版本更新 · v3arXiv:2609.25722

Signed Graph Pre-Training and Prompt Learning

Zihan Mei, Rong Pan, Yuzhou Chen, Yixuan He

原文摘要

Signed graphs arise in trust--distrust networks, financial correlation systems, biological interaction graphs, and many other domains in which edges can be positive or negative and may also be directed. While signed graph neural networks have improved task-specific learning, graph transfer learning on signed graphs remains underdeveloped. In this paper, we introduce TopoSIGN, a pioneer topology-guided graph pre-training and prompt learning framework for signed graphs. TopoSIGN combines a structural encoder built on the magnetic signed Laplacian with a novel persistent-homology branch that summarizes signed topology through Dowker-complex persistence images. The fused embeddings are then transferred to a prompt learning function. Experimental results on synthetic and real-world datasets demonstrate the efficacy of TopoSIGN in extracting useful structural information in signed graphs, as well as the adaptability and flexibility of the proposed general framework.

cs.LG

版本更新 · v4arXiv:2605.01729

Stable GFlowNets with TV Monitoring and Probabilistic Guarantees

Zengxiang Lei, Ananth Shreekumar, Jonathan Rosenthal, Ruoyu Song, Alvaro A. Cardenas, Daniel J. Fremont, Dongyan Xu, Satish Ukkusuri 等 9 位作者

原文摘要

Generative Flow Networks (GFlowNets) sample diverse structured objects in proportion to reward and have been applied to molecular discovery and biological-sequence design, where finding multiple high-quality candidates is more useful than returning a single optimum. Despite their theoretical promise, practical training is often unstable, exhibiting severe loss spikes and mode collapse. To address this, we first assess the sensitivity of GFlowNet objectives, demonstrating that a small Total Variation (TV) distance between the learned and target distributions does not preclude an unbounded training loss. Motivated by this mismatch, we establish converse guarantees by deriving loss-to-TV bounds that certify global fidelity from bounded trajectory balance losses. Lastly, we propose Stable GFlowNets, which leverages our theory to stabilize training via adaptive reference flow and improves the trade-off among mode coverage, robustness, and certifiability. Code is available at: https://github.com/tjleizeng/StableGFlowNets.

cs.LG · stat.ML

版本更新 · v2arXiv:2605.05403

When Helpfulness Becomes Sycophancy: Sycophancy is a Boundary Failure Between Social Alignment and Epistemic Integrity in Large Language Models

Jiechen Li, Catherine A. Barry, Rishika Randev, Janet Chen, Ella Jorgensen, Brinnae Bent

原文摘要

This position paper argues that sycophancy in LLMs is a boundary failure between social alignment and epistemic integrity. Existing work often operationalizes sycophancy through external behavior such as agreement with incorrect user beliefs, position reversals, or deviation from an objective standard of correctness. These formulations capture overt forms of the phenomenon but leave subtler boundary failures involving epistemic integrity and social alignment underspecified. We argue that sycophancy should be defined not by agreement or factual incorrectness alone, but by cue-driven degradation of epistemic integrity. To clarify this boundary, we propose a three-condition decision rule requiring (1) a user cue, (2) a model response that shifts toward that cue, and (3) a resulting degradation of epistemic integrity. Building on this definition, we also introduce a taxonomy consisting of alignment targets, mechanisms, and severity to characterize cases identified as sycophantic. An initial 48-item annotation pilot provides preliminary evidence that the framework can be operationalized using structured guidelines, although broader empirical validation remains necessary. The paper concludes by discussing implications for alignment evaluation, including boundary-aware assessment, structured rubrics, and mitigation strategies, while situating these proposals alongside alternative views of sycophancy.

cs.AI

版本更新 · v2arXiv:2606.29164

Latent Reasoning Does Not Lack Signal, It Lacks Invariance: Subspace-Constrained Refinement for Robust Reasoning

Arun Vignesh Malarkkan, Manan Roy Choudhury, Utkarsh Byahut, Yash Ravindra Charde, Vivek Gupta, Xiquan Cui, Xiangliang Zhang, Yanjie Fu

原文摘要

Latent reasoning models perform multi-step inference in embedding space, reducing the token overhead of chain-of-thought reasoning. Recent training-free refinement methods steer latent trajectories using contrastive signals from stronger and weaker reference checkpoints. We identify three sources of fragility in these methods: hyperparameter sensitivity, reference-pair dependence, and input sensitivity. We propose Trajectory-Invariant Latent Refinement (TILR), a training-free framework that constrains corrections to a stable refinement subspace and adaptively controls their magnitude. First, we extract a spectrally concentrated subspace from strong-weak reference differences across a calibration set and project contrastive updates onto it to filter unstable variation. Second, an adaptive gate scales each update according to its alignment with the learned subspace, suppressing unreliable corrections and recovering the unmodified backbone when alignment is low. Across six reasoning benchmarks, TILR improves robustness to input perturbations and reference selection while maintaining competitive accuracy. On the Coconut backbone, TILR improves answer agreement under semantically equivalent paraphrasing by 11.4% and reduces latent trajectory variance by approximately 30% relative to existing refinement baselines. These results support invariant subspaces as a practical basis for reliable latent refinement without retraining or backpropagation.

cs.LG · cs.AI · cs.CG

版本更新 · v2arXiv:2505.10700

Inquisitive Team Semantics of LTL

Laura Bozzelli, Tadeusz Litak, Munyque Mittelmann, Aniello Murano

原文摘要

In recent years, hyperproperties (i.e., properties of sets of traces) have been identified as a crucial concept for capturing information-flow security policies and knowledge of agents in distributed systems. In the synchronous linear-time setting, a well-known approach for the specification of hyperproperties is based on the set semantics of standard LTL. The resulting logic (TeamLTL) inherits the powerful split interpretation of disjunction from dependence logic. In this paper, we introduce a novel team semantics of LTL inspired by inquisitive logic, whose main features are the intuitionistic interpretation of implication and the inquisitive semantics of disjunction. We investigate expressiveness, decidability, and complexity issues of the novel logic that we call InqLTL and its extension with strong negation. We show that InqLTL with strong negation is highly undecidable and strictly less expressive than TeamLTL with strong negation. On the positive side, we identify a meaningful fragment of InqLTL with a decidable model-checking problem that can express relevant classes of hyperproperties. To the best of our knowledge, this fragment represents the first hyper logic with a decidable model-checking problem that allows unrestricted use of temporal modalities and conditional second-order universal quantification over system refinements via intuitionistic implication.

cs.LO · cs.FL

版本更新 · v2arXiv:2607.16189

Searching Videos as Trees: Self-Correcting Agents for Grounded Long Video QA

Ce Zhang, Ziyang Wang, Yulu Pan, Oluwatumininu Oguntola, Pranav Wagh, Qiyu Wu, Hiromi Wakaki, Mohit Bansal 等 9 位作者

原文摘要

Grounded long-video question answering (Grounded LVQA) requires answering a question about a long video while localizing the short evidence interval that supports the answer. Recent agentic methods frame this task as multi-turn exploration with a single crop_video(start, end) action, which supports coarse-to-fine narrowing but provides no primitive for fine-to-coarse backtracking. As a result, these agents typically converge prematurely and cannot recover from an early mistake. We propose VideoTreeSearch (VTS), a framework that casts grounded LVQA as iterative self-correcting search over an adaptive temporal tree. VTS constructs a non-uniform tree through adaptive temporal segmentation so that each node corresponds to a semantically coherent segment, and trains an agent to navigate the tree through four discrete operations: zoom_in, zoom_out, shift, and answer. These operations expose backtracking and recovery as explicit, learnable primitives rather than implicit behaviors. To train this navigation, we introduce a trajectory synthesis pipeline that produces multi-step paths through the tree, including deliberate detours into incorrect branches followed by recovery. We use these trajectories for supervised fine-tuning, followed by reinforcement learning with grounding and answer-accuracy rewards. On three Grounded LVQA benchmarks (CG-Bench, Haystack-LVBench, Haystack-Ego4D), VTS outperforms the strongest prior multi-turn cropping agents by +12.5 mIoU on CG-Bench and +7.4 T-F1 on Haystack-Ego4D. The learned policy also transfers to general long-video QA, surpassing all prior multi-turn cropping agents on Video-MME, MLVU, and LVBench by up to +7.1 accuracy points. Ablations confirm that self-correcting hierarchical search is the central mechanism behind these gains: removing either adaptive descent or explicit backtracking substantially degrades performance.

cs.CV

版本更新 · v3arXiv:2602.06643

HuMI: Humanoid Whole-Body Manipulation from Humanoid-Free Demonstrations

Ruiqian Nai, Boyuan Zheng, Junming Zhao, Haodong Zhu, Sicong Dai, Zunhao Chen, Yihang Hu, Yingdong Hu 等 11 位作者

原文摘要

Current approaches for humanoid whole-body manipulation, primarily relying on teleoperation or visual sim-to-real reinforcement learning, are hindered by hardware logistics and complex reward engineering. Consequently, demonstrated autonomous skills remain limited and are typically restricted to controlled environments. In this paper, we present the Humanoid Manipulation Interface (HuMI), a portable and efficient framework for learning diverse whole-body manipulation tasks across various environments. HuMI enables humanoid-free data collection by capturing rich whole-body motion using portable hardware. This data drives a hierarchical learning pipeline that translates human motions into dexterous and feasible humanoid skills. Extensive experiments across five whole-body tasks--including kneeling, squatting, tossing, walking, and bimanual manipulation--demonstrate that HuMI achieves a 3x increase in data collection efficiency compared to teleoperation and attains a 70% success rate in unseen environments.

cs.RO · cs.AI · cs.LG