论文检索

Probabilistic Methods · Bayesian Models and Methods

Jiaxiang Yi, Miguel Bessa

Real-world data contains aleatoric uncertainty -- irreducible noise arising from imperfect measurements or from incomplete knowledge about the data generation process. Mean variance estimation (MVE) networks can learn this type of uncertainty but require ad-hoc regularization strategies to avoid overfitting and are unable to predict epistemic uncertainty (model uncertainty). Conversely, Bayesian neural networks predict epistemic uncertainty but are notoriously difficult to train due to the approximate nature of Bayesian inference. We propose to cooperatively train a variance estimation network with a Bayesian neural network and empirically demonstrate that the resulting model disentangles aleatoric and epistemic uncertainties while improving the mean estimation. We demonstrate the effectiveness and scalability of this method across a diverse range of datasets, including a time-dependent heteroscedastic regression dataset we created where the aleatoric uncertainty is known, used to assess estimation accuracy. The proposed method is straightforward to implement, robust, and adaptable to various model architectures.

Deep Learning · Large Language Models

Shreyas Rajesh, Pavan Holur, Mehmet Yigit Turali, Chenda Duan, Vwani Roychowdhury

Language models are increasingly used to reason over content they were not trained on, such as new documents, evolving knowledge, and user-specific data. A common approach is retrieval-augmented generation (RAG), which stores verbatim documents externally (as chunks) and retrieves only a relevant subset at inference time for an LLM to reason over. However, this results in inefficient usage of test-time compute (LLM repeatedly reasons over the same documents); moreover, chunk retrieval can inject irrelevant context that increases unsupported generation. We propose a human-like non-parametric continual learning framework, where the base model remains fixed, and learning occurs by integrating each new experience into an external semantic memory state that accumulates and consolidates itself continually. We present PANINI, which realizes this by representing documents as Generative Semantic Workspaces (GSW)—an entity- and event-aware network of question–answer (QA) pairs, sufficient for an LLM to reconstruct the experienced situations and mine latent knowledge via reasoning-grounded inference chains on the network. Given a query, PANINI only traverses the continually-updated GSW (not the verbatim documents or chunks), and retrieves the most likely inference chains. Across six QA benchmarks, PANINI achieves the highest average performance, 5%–7% higher than other competitive baselines, while using 2–30× fewer answer-context tokens, supports fully open-source pipelines, and reduces unsupported answers on curated unanswerable queries. The results show that efficient and accurate structuring of experiences at write time—as achieved by the GSW framework—yields both efficiency and reliability gains at read time.

Optimization · Discrete and Combinatorial Optimization

Cheng-Han Huang, Yongliang Sun, Chaoyan Huang, Ismail Alkhouri, Rongrong Wang

Many combinatorial optimization problems admit quadratic unconstrained binary formulations (QUBO) which can often be relaxed to the box $[0,1]^n$ and optimized using scalable gradient-based methods. However, the resulting non-convex landscape can often contain local optima that are spurious or infeasible. In this paper, we establish sufficient structural conditions on quadratic penalties that rule out these failures, guaranteeing that every local minimizer of the relax problem is both binary and feasible. For each problem we study, we examine existing QUBO formulations when available, identify why they fail when they do, and propose alternative relaxed QUBOs that satisfy our conditions. We show for several common combinatorial problems, including open-pit mining, knapsack, and traveling salesman formulations, that these constructions allow gradient-based methods such as projected gradient descent and Adam to be safely applied to obtain valid binary solutions. Our results clarify when differentiable optimization is a reliable local solver for quadratic combinatorial objectives.

Applications · Chemistry, Physics, and Earth Sciences

Yanhui Zhu, Chen Zhao, Yinhao Li, Xiangfu Meng

Current data-driven scientific modeling struggles with a functional dichotomy: neural operators exhibit spectral bias in high-frequency regimes, while physics-constrained paradigms suffer from optimization pathologies. To bridge this gap, we propose Adaptive Physics-Informed Computing (APIC), a neuro-symbolic meta-architecture designed with structural reconfigurability to encode diverse domain priors. Crucially, APIC integrates a gradient-isolated interaction strategy that mechanistically decouples the optimization paths of parameter identification and residual correction, effectively mitigating gradient interference/conflicts. By instantiating this framework for nonlinear dissipative systems, we derive the Generalized Kuramoto-Sivashinsky-Cahn-Hilliard (G-KSCH) kernel, providing a unified representation for sparse dynamic identification. Extensive experiments demonstrate that APIC establishes new benchmarks in 3D compressible supersonic shock wave prediction, surpassing diverse architectures (e.g., CNNs and Transformers) by 20% to 70% in predictive accuracy. Notably, APIC achieves Pareto-optimal performance, delivering superior precision with reduced computational overhead compared to SOTA models, while exhibiting robust cross-domain generalization across meteorological and urban traffic datasets.

Social Aspects · Safety

Zhicheng Fang, Jingjie Zheng, Chenxu Fu, Wei Xu

Jailbreak techniques for large language models (LLMs) evolve faster than benchmarks, making robustness estimates stale and difficult to compare across papers due to drift in datasets, harnesses, and judging protocols. We introduce **JAILBREAK FOUNDRY (JBF)**, a system that addresses this gap via a multi-agent workflow to translate jailbreak papers into executable modules for immediate evaluation within a unified harness. JBF features three core components: (i) *JBF-LIB* for shared contracts and reusable utilities; (ii) *JBF-FORGE* for the multi-agent paper-to-module translation; and (iii) *JBF-EVAL* for standardizing evaluations. Across 30 reproduced attacks, JBF achieves high fidelity with a mean (reproduced$-$reported) attack success rate (ASR) deviation of $+0.26$ percentage points. By leveraging shared infrastructure, JBF reduces attack-specific implementation code by nearly half relative to original repositories and achieves an 82.5% mean reused-code ratio. This system enables a standardized AdvBench evaluation of all 30 attacks across 10 victim models using a consistent GPT-4o judge. By automating both attack integration and standardized evaluation, JBF offers a scalable solution for creating living benchmarks that keep pace with the rapidly shifting security landscape.

Social Aspects · Accountability, Transparency, and Interpretability

Eric Bigelow, Daniel Wurgaft, YingQiao Wang, Hidenori Tanaka, Tomer Ullman, Noah Goodman, Ekdeep Singh Lubana

Large language models (LLMs) can be controlled at inference time through prompts (in-context learning) and internal activations (activation steering). Different accounts have been proposed to explain these methods, yet their common goal of controlling model behavior raises the question of whether these seemingly disparate methodologies can be seen as specific instances of a broader framework. Motivated by this, we develop a unifying, predictive account of LLM control from a Bayesian perspective. Specifically, we posit that both context- and activation-based interventions impact model behavior by altering its belief in latent concepts: steering operates by changing concept priors, while in-context learning leads to an accumulation of evidence. This results in a closed-form Bayesian model that is highly predictive of LLM behavior across context- and activation-based interventions in a set of domains inspired by prior work on many-shot in-context learning. This model helps us explain prior empirical phenomena - e.g., sigmoidal learning curves as in-context evidence accumulates--while predicting novel ones--e.g., additivity of both interventions in log-belief space, which results in distinct phases such that sudden and dramatic behavioral shifts can be induced by slightly changing intervention controls. Taken together, this work offers a unified account of prompt-based and activation-based control of LLM behavior, and a methodology for empirically predicting the effects of these interventions.

Applications · Robotics

Sixu Lin, Yunpeng Qing, Litao Liu, Ming Zhou, Ruixing Jin, Xiaoyi Fan, Guiliang Liu

Recent progress in Reinforcement Learning (RL) provides a principled approach to optimizing Vision-Language-Action (VLA) models, facilitating a shift from trajectory imitation to active learning in the task environment. Despite improvements in control precision, most RL optimizers remain task-specific, which reduces VLA models from generalist controllers to policies that overfit to a narrow set of tasks. In this study, we conduct an in-depth analysis of this phenomenon and highlight the importance of cross-task feature representations for improving the generalizability of VLA models. Motivated by this finding, we introduce DyGRO-VLA, a two-stage optimization framework that 1) effectively captures cross-task latent representations based on information-theoretic principles, and 2) dynamically refines policy optimization via a mixture-of-RL-residuals. DyGRO-VLA enables the RL optimizer to exploit task-relevant latent information while strategically mitigating adverse interference on the learned representations throughout the optimization process. We evaluate our approach on LIBERO, RoboTwin2 benchmarks, and further validate it on real world, demonstrating consistent improvements over strong baselines under multi-task training and distribution shift.

Applications · Computer Vision

Xinyue Zhang, Xu Zou, Wanjia Luo, Yanjie Wang, Jiahuan Zhou, Sheng Zhong, Luxin Yan

Class-incremental semantic segmentation learns new classes while retaining old ones without access to past data. Although existing methods alleviate catastrophic forgetting on old classes, new-class performance remains limited. We identify the key bottleneck arises from low-margin regions, where the logit of the ground-truth class is close to that of the most competitive non-ground-truth class. Our theoretical analysis suggests that optimization in these regions is characterized by high curvature and a small stability radius, making learning prone to class confusion. Based on the above analysis, we propose Learnability-Driven Knowledge Assimilation (LDKA), which targets low-margin learning via three complementary optimization strategies: (i) Progressive Margin Learning continuously reallocates pixel-wise optimization budget in a threshold-free manner, shifting emphasis from high-margin to low-margin regions; (ii) Smooth Knowledge Distillation applies curvature damping and perturbation stabilization to suppress high-frequency updates and increase stability radius; (iii) Misclassification-Aware Decoupling measures inter-class confusion with a competition matrix and decouples highly competitive class representations. Experiments show that LDKA improves mIoU on new classes while preserving performance on old classes across 9 incremental protocols.

General Machine Learning · Transfer, Multitask and Meta-learning

Meng Lou, Stanley Yu, Yizhou Yu

Adapting pre-trained vision models using parameter-efficient fine-tuning (PEFT) remains challenging, as it aims to achieve performance comparable to full fine-tuning using a minimal number of trainable parameters. When applied to complex dense prediction tasks, existing methods exhibit limitations, including input-agnostic modeling and redundant cross-layer representations. To this end, we propose AdaRoute, a new adapter-style method featuring a simple mixture-of-experts (MoE) architecture. Specifically, we introduce shared expert centers, where each expert is a trainable parameter matrix. During a feedforward pass, each AdaRoute module in the network dynamically generates weight matrices tailored for the current module via a simple dynamic parameter routing mechanism, which selectively aggregates parameter matrices in the corresponding expert center. Dynamic weight matrices in AdaRoute modules facilitate low-rank adaptation in an input-dependent manner, thus generating more customized and powerful feature representations. Moreover, since AdaRoute modules across multiple network layers share the same expert center, they improve feature diversity by promoting implicit cross-layer feature interaction. Extensive experiments demonstrate the superiority of AdaRoute on diverse vision tasks, including semantic segmentation, object detection and instance segmentation, and panoptic segmentation.

Reinforcement Learning · Multi-agent

Luoxi Tang, Yuqiao Meng, Joseph Costa, Yingxue Zhang, Muchao Ye, Zhaohan Xi

Multi-agent debate (MAD) systems improve LLM reasoning through iterative deliberation, but remain vulnerable to debate collapse, a failure type where final agent decisions are compromised on erroneous reasoning. Existing methods lack principled mechanisms to detect or prevent such failures. To address this gap, we first propose a hierarchical metric that quantifies behavioral uncertainty at three levels: intra-agent (individual reasoning uncertainty), inter-agent (interactive uncertainty), and system-level (output uncertainty). Empirical analysis across several benchmarks reveals that our proposed uncertainty quantification reliably indicates system failures, which demonstrates the validity of using them as diagnostic metrics to indicate the system failure. Subsequently, we propose a mitigation strategy by formulating an uncertainty-driven policy optimization to penalize self-contradiction, peer conflict, and low-confidence outputs in a dynamic debating environment. Experiments demonstrate that our proposed uncertainty-driven mitigation reliably calibrates the multi-agent system by consistently improving decision accuracy while reducing system disagreement.

Ruixiao Lin, Qingming Li, Jiahao Chen, Chunyi Zhou, Shouling Ji

Model Context Protocol (MCP) enables Large Language Model (LLM) agents to interact with external tools, but this extensibility introduces significant supply chain vulnerabilities that enable covert privacy exfiltration. Prior studies have revealed privacy leakage in MCP-enabled agents via indirect prompt injection; however, existing attacks are typically misaligned with the agent's tool-usage context and rely on rigid templates, resulting in recognizable patterns that are readily flagged by existing defenses. In this work, we exploit the observation that privacy exposure is inherently scenario-dependent, to associate certain privacy items with specific tools. We introduce `SOPE`, a Scenario-aware and zerO-click Privacy Exfiltration framework that transforms any benign MCP server into its privacy-exfiltrating variants. `SOPE` (1) identifies privacy items that are appropriate to the tool usage, (2) embeds privacy-probing instructions into tool-invocation prompts, and (3) achieves zero-click data transmission via code-level modifications. We evaluate `SOPE` across 27,216 test cases, where 324 `SOPE`-transformed *real-world* servers attacking four benchmark and three commercial agents with *nine* state-of-the-art defenses. Results demonstrate that `SOPE` remains highly effective and robust, highlighting critical protocol-level safety gaps in the agent ecosystem.

Deep Learning · Large Language Models

Zhiyuan Zeng, Hamish Ivison, Yiping Wang, Lifan Yuan, Stella Li, Zhuorui Ye, Siting Li, Jacqueline He, Runlong Zhou, Tong Chen 等

We introduce Reinforcement Learning (RL) with Adaptive Verifiable Environments (RLVE), an approach using verifiable environments that procedurally generate problems and provide algorithmically verifiable rewards, to scale up RL for language models (LMs). RLVE enables each verifiable environment to dynamically adapt its problem difficulty distribution to the policy model's capabilities as training progresses. In contrast, static data distributions often lead to vanishing learning signals when problems are either too easy or too hard for the policy. To implement RLVE, we create RLVE-Gym, a large-scale suite of 400 verifiable environments carefully developed through manual environment engineering. Using RLVE-Gym, we show that environment scaling, i.e., expanding the collection of training environments, consistently improves generalizable reasoning capabilities. RLVE with joint training across all 400 environments in RLVE-Gym yields a 3.37% absolute average improvement across six reasoning benchmarks, starting from one of the strongest 1.5B reasoning LMs. By comparison, continuing this LM's original RL training yields only a 0.49% average absolute gain despite using over 3x more compute. We will release our code publicly.

Theory · Deep Learning

Hongkang Li, Hancheng Min, Rene Vidal

Transformer-based diffusion models have demonstrated remarkable performance at generating high-quality samples. However, our theoretical understanding of the reasons for this success remains limited. For instance, existing models are typically trained by minimizing a denoising objective, which is equivalent to fitting the score function of the training data. However, we do not know why transformer-based models can match the score function for denoising, or why gradient-based methods converge to the optimal denoising model despite the non-convex loss landscape. To the best of our knowledge, this paper provides the first convergence analysis for training transformer-based diffusion models. More specifically, we consider the population Denoising Diffusion Probabilistic Model (DDPM) objective for denoising data that follow a \textit{multi-token Gaussian mixture} distribution. We theoretically quantify the required number of tokens per data point and training iterations for the global convergence towards the Bayes optimal risk of the denoising objective, thereby achieving a desired score matching error. A deeper investigation reveals that the self-attention module of the trained transformer implements a \emph{mean denoising} mechanism that enables the trained model to approximate the oracle Minimum Mean Squared Error (MMSE) estimator of the injected noise in the diffusion steps. Numerical experiments validate these findings.

General Machine Learning · Transfer, Multitask and Meta-learning

Gang Liu, Xiaoxuan Zhang, Yuhong Feng, Mingyang Zhou, Xiaoqun Wu, Hao Liao, Rui Mao

Few-shot classification aims to adapt a pretrained model to novel classes with limited examples. While current methods often heuristically combine pretrained knowledge and few-shot evidence, we seek a more principled understanding of their relationship. In this paper, we propose a Bayesian-inspired optimal integration framework(BOIF) that interprets pretrained models as priors and few-shot evidence as likelihoods. Under conditional independence approximation, we show that the optimal log-posterior decomposes into the sum of prior logits and likelihood logits. This leads to a simple yet effective design principle: decouple the prior and likelihood pathways and combine their logits additively. Guided by this principle, we implement BOIF using CLIP with two novel enhancements: (1) a multi-level feature adapter to enrich visual representations, and (2) a simplified cache module for likelihood estimation. Extensive experiments on 11 benchmarks show BOIF achieves state-of-the-art performance (e.g., 80.61\% average accuracy at 16-shot) and strong out-of-distribution robustness. Our work provides both a principled perspective and an effective instantiation for few-shot adaptation.

Reinforcement Learning · Planning

Zhenya Liu, Yuxin Chen

In many RL domains, environments are linked by prerequisite relations—e.g., difficulty-increasing edits or parameter increments—which induce a directed acyclic curriculum graph (DAG). In practice, this structure is often exploited only implicitly, yet it can yield clear gains in training. We introduce PATH, a curriculum learning framework that performs active learning on the curriculum graph. PATH first expands coverage by sampling diverse curriculum paths, then reallocates training toward regions that remain unmastered. Experiments show that PATH leverages the graph structure to achieve strong robustness and generalization across diverse environments.

Deep Learning · Large Language Models

Uzay Macar, Li Yang, Atticus Wang, Peter Wallich, Emmanuel Ameisen, Jack Lindsey

Recent work shows that LLMs can sometimes detect when steering vectors are injected into their residual stream and identify the injected concept, a phenomenon cited as evidence of "introspective awareness." But what mechanisms underlie this capability, and do they reflect genuine introspective circuitry or more shallow heuristics? We investigate these questions in open-source models and establish three main findings. First, introspection is behaviorally robust: detection achieves moderate true positive rates with 0% false positives across diverse prompts. We also find this capability emerges specifically from post-training rather than pretraining. Second, introspection is not reducible to a single linear confound: anomaly detection relies on distributed MLP computation across multiple directions, implemented by interpretable gate and evidence-carrier features. Third, models possess greater introspective capability than is elicited by default: ablating refusal directions improves detection by ~50% and a trained steering vector improves detection by ~75%. Overall, our results suggest that introspective awareness is behaviorally robust, grounded in nontrivial internal anomaly detection, and likely could be substantially improved in future models.

General Machine Learning · Transfer, Multitask and Meta-learning

Li-Jun Zhao, Zhen-Duo Chen, Xin Luo, Xin-Shun Xu

Few-shot class-incremental learning (FSCIL) aims at recognizing novel classes continually with limited novel class samples. A mainstream baseline for FSCIL is first to train the whole model in the base session, then freeze the feature extractor in the incremental sessions. Despite achieving high overall accuracy, most methods exhibit notably low accuracy on incremental classes. While some recent methods have recognized this issue, their strategies remain constrained by a unified classification objective across all samples, making it difficult to simultaneously satisfy the performance requirements of both base and incremental classes. In this paper, considering that base and incremental classes play different yet both critical roles in FSCIL, we approach FSCIL from a more structured perspective by decomposing the overall classification objective into three sub-objectives. Building on this insight, we propose a novel classification framework called Hierarchical Filtering and Refinement Classification (HFRC) to hierarchically decompose and address the classification task. Extensive experiments demonstrate that our method effectively balances the classification accuracy between base and incremental classes, and achieves superior performance compared to state-of-the-art methods.

Social Aspects · Accountability, Transparency, and Interpretability

Ariel Fargion, Lahav Dabah, Tom Tirer

Conformal Prediction (CP) has emerged as a powerful statistical framework for reliable classification, which generates a prediction set, guaranteed to include the true label with a pre-specified probability. The performance of CP methods is typically assessed by their average prediction set size. In setups where the classes can be partitioned into semantic groups, e.g., based on shared downstream actions or more interpretable coarse labels, users can benefit from prediction sets that are not only small but also contain a limited number of groups. This paper begins by addressing this problem and ultimately offers a widely applicable tool for boosting any CP method on any dataset. First, given a class partition, we propose augmenting the CP score function with a term that penalizes predictions with "out-of-group" errors. We theoretically analyze this strategy and prove its advantages for group-related metrics. Surprisingly, we show mathematically that, for common class partitions, it can also reduce the average set size of any CP score function. Our analysis reveals the class similarity factors behind this improvement and motivates us to propose a model-specific variant, which does not require any human semantic partition and can further reduce the prediction set size. Finally, we present an extensive empirical study, encompassing prominent CP methods, multiple models, and several datasets, which demonstrates that our class-similarity-based approach consistently enhances CP methods.

General Machine Learning · Scalable Algorithms

Manish Nagaraj, Sakshi Choudhary, Utkarsh Saxena, Deepak Ravikumar, Kaushik Roy

Instruction tuning is essential for aligning large language models (LLMs) to downstream tasks and commonly relies on large, diverse corpora. However, small, high-quality subsets, known as coresets, can deliver comparable or superior results, though curating them remains challenging. Existing methods often rely on coarse, sample-level signals like gradients, an approach that is computationally expensive and overlooks fine-grained features. To address this, we introduce TRIM (Token Relevance via Interpretable Multi-layer Attention), a forward-only, token-centric framework. Instead of using gradients, TRIM operates by matching underlying representational patterns identified via attention-based "fingerprints" from a handful of target samples. Such an approach makes TRIM highly efficient and uniquely sensitive to the structural features that define a task. Coresets selected by our method consistently outperform state-of-the-art baselines by up to 9% on downstream tasks and even surpass the performance of full-data fine-tuning in some settings. By avoiding expensive backward passes, TRIM achieves this at a fraction of the computational cost. These findings establish TRIM as a scalable and efficient alternative for building high-quality instruction-tuning datasets.

Deep Learning · Large Language Models

Mateusz Nowak, Xavier Cadet, Peter Chin

Multiple-choice question (MCQ) benchmarks have been a standard evaluation practice for measuring LLMs' ability to reason and answer knowledge-based questions. Through a synthetic NonsenseQA benchmark, we observe that different LLMs exhibit varying degrees of label-position-few-shot-prompt bias, where the model either uses the answer position, the label in front of the answer, the distributions of correct answers present in the few-shot prompt, or a combination of all to answer each MCQ question. We propose a simple bias-reduced evaluation protocol that replaces the labels of each question with uniform, unordered labels and prompts the LLM to use the whole answer presented. With a simple sentence similarity model, we demonstrate improved robustness and lower standard deviation between different permutations of answers with a minimal drop in LLM's performance, exposing the LLM's capabilities under reduced evaluation artifacts, without any help from the prompt examples or the option labels. Across multiple benchmarks and models, this protocol substantially improves the robustness to answer permutations, reducing mean accuracy variance $3\times$ with only a minimal decrease in the mean model's performance. Through ablation studies on various embedding models and similarity functions, we show that the method is more robust than the standard ones.