论文检索

Deep Learning · Large Language Models

Anna Mészáros, Patrik Reizinger, Ferenc Huszár

Modern decision transformers, trained similarly to LLMs, can achieve strong in-distribution performance in complex sequential domains like chess, but it remains unclear to what extent they reason systematically about rules and strategy. We study the reasoning capabilities of a 270M-parameter chess transformer trained via behavior cloning on standard chess. To investigate its abilities, we construct out-of-distribution test sets ---including board states and variants never seen during training---designed to reveal failures of systematic generalization. Our analysis shows that the model exhibits robust rule-based reasoning, consistently generating legal moves in novel configurations, but its strategic reasoning is more limited. The model generates high-quality moves on curated OOD puzzles and shows basic strategy adaptation in full games. It underperforms symbolic AI algorithms that rely on explicit search, although the performance gap is smaller when playing against human users on Lichess. Moreover, the training dynamics reveals distinct phases in how the model learns to respect the fundamental constraints, suggesting an emergent compositional understanding of the game.

Applications · Language, Speech and Dialog

Sepehr Dehdashtian, Jacob Seidman, Vishnu Boddeti, Gaurav Bharaj

Audio deepfake detection (ADD) models are critical for countering the malicious use of text-to-speech (TTS) models. Evaluating and strengthening ADD models requires developing datasets that span the space of generated audio and highlight high-error regions. Existing dataset development strategies face two challenges: (i) manual collection, and (ii) inefficient discovery of blind spots in the ADD models. To address these challenges, we propose FoeGlass, the first black-box automated red-teaming method for ADDs, which effectively discovers ADD failure modes in the space of generated audio underexplored by state-of-the-art deepfake benchmarks. FoeGlass uses the in-context learning capabilities of an LLM to explore the input space of a TTS model, generating audio samples that fool the target ADD using only black-box access to all components. By using a carefully designed context based on diversity measurements, FoeGlass mitigates the common problem of mode collapse in automated red-teaming systems. Empirical evaluations on several open-source ADD and TTS models demonstrate that data generated from FoeGlass substantially improves the false negative rates over unconditional sampling baselines and recent spoofing datasets by up to 94%, while requiring no manual supervision. Furthermore, we show that the attacks generated by FoeGlass are transferable across different target ADDs, demonstrating its broad applicability and ease of use for the automated red teaming of ADD systems. Finally, fine-tuning ADD models on FoeGlass-generated samples notably enhances the robustness of the detectors (up 41%).

Deep Learning · Large Language Models

Yuanhao Li, Hongbo Wang, Xiaotang Shang, Xunzhu Tang, Yiming Cao, Xuhong Chen

Reinforcement learning for program repair is hindered by sparse execution feedback and coarse sequence-level rewards that obscure which edits actually fix bugs. We present BoostAPR, a three-stage framework: (1) supervised fine-tuning on execution-verified demonstrations with reasoning traces, (2) training dual reward models—a sequence-level assessor and a line-level credit allocator—from execution outcomes, and (3) PPO optimization where the line-level model redistributes rewards to critical edit regions. This line-level credit assignment operates at an intermediate granularity naturally suited to code changes. Trained on SWE-Gym and evaluated on four benchmarks, BoostAPR achieves 40.7% on SWE-bench Verified (+22.9pp over the base model), 24.8% on Defects4J (Python→Java transfer), 84.5% on HumanEval-Java, and 95.0% on QuixBugs, showing competitive open-source performance with strong cross-language generalization.

Applications · Computer Vision

Jiahao Chen, Yipeng Qin, Ganlong Zhao, Xin Li, Wenping Wang, Guanbin Li

3D Gaussian Splatting (3DGS) has demonstrated remarkable performance in novel view synthesis and 3D scene reconstruction, but its quality often degrades in real-world environments due to transient distractors, such as moving objects and varying shadows. Existing methods commonly rely on semantic cues extracted from pre-trained vision models to identify and suppress these distractors, but such semantics are misaligned with the binary distinction between static and transient regions and remain fragile under the appearance perturbations introduced during 3DGS optimization. We propose 3DGS-HPC, a framework that circumvents these limitations by combining two complementary principles: a patch-wise classification strategy that leverages local spatial consistency for robust region-level decisions, and a hybrid classification metric that adaptively integrates photometric and perceptual cues for more reliable separation. Extensive experiments demonstrate the superiority and robustness of our method in mitigating distractors to improve 3DGS-based novel view synthesis. The code will be released.

Theory · Probabilistic Methods

Mengda Li, Zeng Li, Jianfeng Yao

Removing noise is difficult, but adding noise is easy. In this work, we show how to eliminate mean-shift noisy components from PCA by deliberately introducing knockoff mean-shift perturbation. Standard PCA is highly sensitive to shifts in the sample mean: a small fraction of samples from a shifted distribution can cause large deviations in the leading principal components. In high-dimensional regimes, existing Robust PCA approaches cannot handle the mean-shift contamination structure inherent in the mixture model. Using tools from Random Matrix Theory, we prove that the mean-shift spikes are spectrally separable from the stable eigenvalues of the original covariance. Furthermore, the original eigenspace remains asymptotically invariant to the contamination, independent of the mixture weight. Exploiting this spectral stability, we propose a simple, two-stage PCA algorithm by adding knockoff mean that identifies and removes the mean-shift component using only standard PCA operations. We release an implementation for main code at https://anonymous.4open.science/r/ms-pca-0E47/.

Anyuan Zhuo, Xuefei Ning, Ningyuan Li, Jingyi Zhu, Yu Wang, Pinyan Lu

This work investigates the resilience of contemporary large language models (LLMs) against frequent character-level perturbations. We examine three types of character-level perturbations including introducing numerous typos within words, shuffling the characters in each word, and inserting a large number of invisible characters into the text. Surprisingly, even under severe perturbation, such as shuffling nearly all words character-wise to produce text that is almost unreadable to humans, or inserting invisible characters which are several times more than the visible ones as noise, many LLMs still maintain notable performance. We explore the underlying causes of this robustness and find that LLMs exhibit remarkable resilience to chaotic segmentation and fragmented tokenization. Furthermore, we examine the mechanisms by which LLMs remove perturbations to correctly comprehend text, including both implicit and explicit mechanisms for character-level perturbation. We hope that our findings on the low-level robustness of LLMs will unveil their inherent architectural strengths, reveal the potential risks of their misuse, and inform the reliable deployment of LLMs across diverse application scenarios.

Deep Learning · Large Language Models

Yi Xie, Siao Liu, Falong FAN, Yuanqi Yao, Siyang Cao, Yue Zhao, Bo Liu

Multi-agent LLM systems can improve reasoning and tool use, yet recent evidence shows their gains are often unstable and sensitive to interaction design. A promising direction is to \emph{train} collaboration, but team post-training introduces a moving-target effect: when agents interact through a shared context, updating one agent shifts the context distribution faced by the others, which can regress coordination under naive sequential updates. We propose \textit{TeamTR}, a trust-region framework for fine-tuning heterogeneous LLM teams that explicitly controls this \emph{occupancy shift}. TeamTR evaluates each agent update on rollouts from the \emph{intermediate} team induced by partially applied updates, and enforces per-agent trust regions via a token-decomposed \emph{reverse} KL that is directly monitorable from those rollouts. This yields population-level per-update and per-stage \emph{improvement lower bounds} whose functional form applies to any realized update order, and motivates a practical certificate \emph{proxy} computed from logged surrogates and KL terms. We instantiate TeamTR for router-based text handoff with sequence-level returns and bounded group-normalized advantages, and show empirically that it mitigates coordination regressions, improves training stability across heterogeneous teams, and supports modular component replacement via a trust-region alignment step.

Applications · Time Series

Junru Zhang, Lang Feng, Haoran Shi, Xu Guo, Han Yu, Yabo Dong, Duanqing Xu

Time-series anomaly detection (TSAD) with multimodal large language models (MLLMs) is an emerging area, yet a persistent challenge remains: MLLMs rely on coarse time-series heuristics but struggle with multi-dimensional, detailed reasoning, which is vital for understanding complex time-series data. We present AnomSeer to address this by reinforcing the model to ground its reasoning in precise, structural details of time series, unifying anomaly classification, localization, and explanation. At its core, an expert chain-of-thought trace is generated to provide a verifiable, fine-grained reasoning from classical analyses (e.g., statistical measures, frequency transforms). Building on this, we propose a novel time-series grounded policy optimization (TimerPO) that incorporates two additional components beyond standard reinforcement learning: a time-series grounded advantage based on optimal transport and an orthogonal projection to ensure this auxiliary granular signal does not interfere with the primary detection objective. Across diverse anomaly scenarios, AnomSeer, with Qwen2.5-VL-3B/7B-Instruct, outperforms larger commercial baselines in classification and localization accuracy, particularly on point- and frequency-driven exceptions. Moreover, it produces plausible reasoning traces that support its conclusions.

Deep Learning · Large Language Models

David Wan, Han Wang, Ziyang Wang, Elias Stengel-Eskin, Hyunji Lee, Mohit Bansal

Multimodal large language models (MLLMs) are increasingly used for real-world tasks involving multi-step reasoning and long-form generation, where reliability requires grounding model outputs in heterogeneous input sources and verifying individual factual claims. However, existing multimodal grounding benchmarks and evaluation methods focus on simplified, observation-based scenarios or limited modalities and fail to assess attributions in complex multimodal reasoning. We introduce MURGAT (Multimodal Reasoning with Grounded Attribution), a benchmark for evaluating fact-level multimodal attribution in settings that require reasoning beyond direct observation. Given inputs spanning video, audio, and other modalities, MURGAT requires models to generate answers with explicit reasoning and precise citations, where each citation specifies both modality and temporal segment. To enable reliable assessment, we introduce an automatic evaluation framework that strongly correlates with human judgments (r = 0.84). Benchmarking against human and automated scores reveals that even strong MLLMs frequently hallucinate citations despite correct reasoning. Moreover, we see a key trade-off: increasing reasoning depth or enforcing structured grounding often degrades accuracy, highlighting a significant gap between internal reasoning and verifiable attribution

Reinforcement Learning · Deep RL

Taeyoung Yun, Pierre-Luc St-Charles, Jinkyoo Park, Yoshua Bengio, Minsu Kim

We address the challenge of automatically generating diverse attack prompts for large language models (LLMs) that elicit harmful behaviors (e.g., insults, sexual content) and are used for safety fine-tuning. While several prior approaches train LLMs with reinforcement learning (RL) to generate such prompts using only a toxicity classifier as a reward, existing diversity-seeking RL methods often collapse to limited modes: once high-reward prompts are found, exploration of new regions is discouraged. Inspired by the active learning paradigm that encourages adaptive exploration, we introduce \textbf{Active Attacks}, a novel RL-based red-teaming algorithm that adapts its attacks as the victim evolves. By periodically safety fine-tuning the victim LLM with collected attack prompts, we naturally induce an \emph{easy-to-hard exploration curriculum}, where the attacker progresses beyond easy modes toward increasingly difficult ones. We observe that this simple plug-and-play module, which seamlessly integrates into existing RL objectives, unexpectedly outperformed prior RL-based methods, improving cross-attack success rates against GFlowNets, the previous state-of-the-art, from 0.07\% to 31.28\% (a relative gain of more than 400×) with only a 6\% increase in computation.

Applications · Chemistry, Physics, and Earth Sciences

Zhao Yanshun, Xiaoyu Peng, Congcong Zhu, Jiamin Jiang, Jingrun Chen

Conventional patchified Transformers operate on uniform spatial partitions, distributing computational effort evenly across the domain irrespective of local features. This inflexible tokenization scheme is inherently limited in its ability to efficiently represent and process solutions to complex PDEs. To address this, we propose MeshTok, an adaptive mesh refinement (AMR)-inspired tokenization and sequence modeling framework. This method selectively refines spatial regions exhibiting sharp gradients, transient features, or multiscale structures, generating a heterogeneous set of multiscale tokens defined on a fixed simulation grid. These tokens are processed within a unified Transformer sequence, enabling the model to simultaneously capture coarse-grained global context and fine-grained local details without requiring specialized architectural components. Although adaptive refinement moderately increases token count, it promotes a more targeted allocation of computational resources to physically informative regions, thereby enhancing predictive accuracy under equivalent computational constraints. Experimental evaluations across multiple PDE families and benchmark datasets demonstrate that MeshTok consistently improves the efficiency–accuracy trade-off compared to uniform-grid baselines. This suggests adaptive multiscale tokenization as a scalable and generalizable design principle for neural PDE modeling.

Social Aspects · Everything Else

Maria Despoina Siampou, Shushman Choudhury, Shang-Ling Hsu, Neha Arora, Cyrus Shahabi

Recent progress in geospatial foundation models highlights the importance of learning general-purpose representations for real-world locations, particularly points-of-interest (POIs) where human activity concentrates. Existing approaches, however, focus primarily on place identity derived from static textual metadata, or learn representations tied to trajectory context, which capture movement regularities rather than how places are actually used (i.e., POI's function). We argue that POI function is a missing but essential signal for general POI representations. We introduce Mobility-Embedded POIs (ME-POIs), a framework that augments POI embeddings derived, from language models with large-scale human mobility data to learn POI-centric, context-independent representations grounded in real-world usage. ME-POIs encodes individual visits as temporally contextualized embeddings and aligns them with learnable POI representations via contrastive learning to capture usage patterns across users and time. To address long-tail sparsity, we propose a novel mechanism that propagates temporal visit patterns from nearby, frequently visited POIs across multiple spatial scales. We evaluate ME-POIs on five newly proposed map enrichment tasks, testing its ability to capture both the identity and function of POIs. Across all tasks, augmenting text-based embeddings with ME-POIs consistently outperforms both text-only and mobility-only baselines. Notably, ME-POIs trained on mobility data alone can surpass text-only models on certain tasks, highlighting that POI function is a critical component of accurate and generalizable POI representations.

Applications · Time Series

Nassim Oufattole, Matthew McDermott, Collin Stultz

Autoregressive generative models for irregularly sampled clinical time-series data are increasingly used for zero-shot risk forecasting. Prior work typically adopts a single fine-grained discretization of time, where tokens are generated at one fixed, pre-determined, temporal resolution. We demonstrate that zero-shot accuracy for a given task varies depending on the temporal dynamics of the task in question, where performance will be low when the temporal dynamics is not well-matched to temporal resolution of the generative model. We then propose MoRGen (Mixture-of-Resolutions Generation), which fuses zero-shot generative experts trained at multiple resolutions, to improve zero-shot performance across tasks with very different temporal dynamics. Across multiple horizons and outcomes on three independent clinical datasets, MoRGen achieves lower binary-cross entropy (BCE) and statistically significant AUROC gains over autoregressive generative models that forecast tokens at a fixed temporal resolution.

Applications · Computer Vision

Longyu Yang, Jun Liu, Yap-Peng Tan, Fumin Shen, Heng Tao Shen, Xiaofeng Zhu, Ping Hu

LiDAR point cloud anomaly detection is critical for autonomous system safety, yet most existing methods rely only on visible measurements, overlooking occlusion as a structured consequence of the LiDAR sensing process. We argue that anomalies are characterized not only by what is observed, but also by the spatial voids they create, which alter occlusion patterns and volumetric visibility. We propose Counterfactual Occlusion-Visibility Anomaly Learning (COVAL), a framework that intervenes on volumetric visibility during training. Using physics-conformed synthetic anomaly construction, COVAL generates paired factual and counterfactual observations with identical scene geometry but different occlusion patterns. Then, we introduce two complementary objectives: Visibility-Variant Counterfactual Reconstruction, which models occlusion-induced missing regions, and Visibility-Invariant Counterfactual Consistency, which enforces stable representations across visibility changes. Together, these objectives isolate anomaly-induced structural missingness and in turn refine representation of normal scenes, thus improving anomaly sensitivity at test time. Experiments on standard LiDAR anomaly segmentation benchmarks show that COVAL achieves state-of-the-art performance.

Theory · Optimization

PAUL DUETTING, Federico Fusco, Silvio Lattanzi, Ashkan Norouzi-Fard, Ola Svensson, Morteza Zadimoghaddam

Consistency is an important property in dynamic submodular maximization and entails maintaining a near-optimal solution at all times, making only a small number of adjustments to the solution in each step. Prior work has explored this question for the insertion-only case, where the algorithm faces a stream of $n$ insertions, and has established lower and upper bounds for the cardinality-constrained version of the problem. We consider this question in the fully dynamic setting, where the stream of operations may contain both insertions and deletions. We develop a general framework for designing algorithms for this setting, and instantiate it to obtain the first constant-factor approximations with sublinear consistency. For cardinality constraints, we propose a $\tfrac 12 - O(\varepsilon)$ approximation that is $O\left(\tfrac{1}{\varepsilon^2}\right)$ consistent. For rank-$k$ matroid constraints, we construct a $\tfrac 14 - O(\varepsilon)$ approximation to the dynamic optimum that is $O\left(\tfrac{\log k}{\varepsilon^2}\right)$ consistent.

Deep Learning · Attention Mechanisms

Nhat Thanh Tran, Fanghui Xue, shuai zhang, Jiancheng Lyu, Yunling Zheng, YINGYONG QI, Jack Xin

Attention is the critical component of a transformer. Yet the quadratic computational complexity of vanilla full attention in the input size and the inability of its linear attention variant to focus have been challenges for computer vision tasks. We provide a mathematical definition of generalized attention and formulate both vanilla softmax attention and linear attention within the general framework. We prove that generalized attention disperses, that is, as the number of keys tends to infinity, the query assigns equal weights to all keys. Motivated by the dispersion property and recent development of Mamba form of attention, we design Scalable and Efficient Mamba like Attention (SEMA) which utilizes token localization to avoid dispersion and maintain focusing, complemented by theoretically consistent arithmetic averaging to capture global aspect of attention. We support our approach on Imagenet-1k where classification results show that SEMA is a scalable and effective alternative beyond linear attention, outperforming recent vision Mamba models on increasingly larger scales of images at similar model parameter sizes.

Xingchen Hu, Miao Jia, Jiyuan Liu, Siwei Wang, KE LIANG, Wenjing Yang

Multi-view clustering (MVC) is a fundamental task in heterogeneous data analysis, where anchor-based graph methods are widely adopted for their computational efficiency. However, existing approaches typically utilize static, single-layer anchors, failing to capture the multi-granularity nature of complex data. Drawing inspiration from hierarchical human cognition, we propose a hierarchical anchor graph learning method, termed HAG-MVC, a novel framework that organizes multi-view data as a multi-level pyramid. Unlike conventional one-shot anchor generation methods, HAG-MVC introduces a multi-level co-evolution mechanism, where anchors and graph structures are iteratively refined together to capture semantics from fine-to-coarse granularities. Moreover, HAG-MVC offers a transparent abstraction architecture as an alternative to black-box deep clustering: by maintaining all anchors within the original feature space, it enables explicit inspection of the abstraction process, ensuring inherent interpretability. Extensive experiments on benchmark datasets demonstrate that HAG-MVC consistently outperforms state-of-the-art methods. Beyond MVC, this work provides a scalable and trustworthy paradigm for hierarchical knowledge representation in broad machine learning tasks.

Deep Learning · Large Language Models

Ruiyang Qin, Qingzhuo Wang, Tian Wang, Zhihua Wei, Wen Shen

The remarkable capabilities of large language models (LLMs) are often undermined by their instability. Even subtle and semantically irrelevant changes in prompts can cause dramatic fluctuations in performance, a phenomenon known as prompt sensitivity. Previous studies typically evaluate prompt sensitivity by comparing the LLM's final outputs when prompts change. However, such coarse-grained metrics fail to explain the internal reasons for prompt sensitivity. In this paper, we introduce interactions as a fine-grained tool to analyze prompt sensitivity of LLMs. Specifically, we decompose the output score of the LLM into a set of interactions. Each interaction represents a nonlinear relationship involving a set of input variables. We discover that subtle changes to prompts can trigger severe instability in interactions, even when the outputs of the LLM remain the same. To this end, we propose an Interaction-based Prompt Sensitivity (IPS) metric by quantifying changes in interactions when we introduce subtle changes to prompts. We apply the IPS metric to 50 open-source LLMs and uncover four factors that reduce the prompt sensitivity of LLMs, including supervised fine-tuning, increased model scales, dense architectures, and few-shot learning. More crucially, we discover a common mechanism by which these four factors reduce prompt sensitivity: all four factors tend to reduce the prompt sensitivity of low-order interactions (i.e., interactions involving few input variables).

General Machine Learning · Evaluation

Apurva Gandhi, Vishwas Suryanarayanan, Firoz Shaik, Raja Anwar, Shubhang Desai, Thong Nguyen, Muhammad Raza, Vishal Chowdhary, Graham Neubig

Creating and editing slides is a rich, multimodal activity that is ubiquitous in professional and educational settings, making it an ideal testbed for real-world computer-use agents. Microsoft PowerPoint is among the most widely adopted and feature-rich environments for presentation creation. We introduce PPT-Eval, a benchmark of 120 diverse PowerPoint tasks across 12 files that cover both content creation and presentation editing scenarios, organized by difficulty. A central challenge in this domain is evaluation: tasks are complex, multimodal, and often admit many valid solutions. Moreover, today’s agents frequently make only partial progress, which binary success metrics fail to capture. To address this, we design a robust evaluation framework to help create task-specific rubrics for PowerPoint tasks, taking inspiration from and building on past works for rubric-based evaluation. These rubrics award partial credit for intermediate steps, penalize unnecessary changes and poor aesthetics, and provide natural language feedback. This nuanced approach proves highly effective, achieving a Kendall's $\tau_b$ correlation of 0.77 with human judgments. We find that existing frontier agents still struggle with solving PowerPoint tasks, with strong models like Claude-4.5-Opus achieving only a 43\% success rate and an average partial score of 59\%.

Social Aspects · Safety

Simon Storf, Rich Barton-Cooper, James Peters-Gill, Marius Hobbhahn

Safe deployment of Large Language Model (LLM) agents in autonomous settings requires reliable oversight mechanisms. A central challenge is detecting *scheming*, where agents covertly pursue misaligned goals. One approach to mitigating such risks is LLM-based monitoring: using language models to examine agent behaviors for suspicious actions. We study *constitutional black-box monitors*: prompted classifiers that detect scheming using only externally observable inputs and outputs, optimized on synthetic data generated from natural-language behavior specifications. We introduce two pipelines for generating synthetic agent trajectories, *STRIDE* (iterative refinement) and *Gloom* (agent-environment simulation), from which we generate 1,000 samples each. We optimize monitors on these datasets via prompt sweeps, human refinement, and automated prompt optimization, and evaluate performance on 7,500 held-out trajectories from Control Arena, a suite of grounded environments where agents operate in more realistic contexts. Our results demonstrate that monitors selected purely on synthetic data can generalize to more realistic environments, capturing a meaningful scheming signal. However, we find that performance saturates quickly in our setting, with simple prompt sweeps matching the results of more extensive optimization. Pushing beyond this limit yields no further improvements and instead leads to overfitting.