论文检索

Applications · Computer Vision

Chaoyu Li, Tianzhi Li, Fei Tao, ZHENYU ZHAO, Ziqian Wu, Maozheng Zhao, Juntong Song, Cheng Niu, Pooyan Fazli

Vision-language models (VLMs) advance video understanding but operate under tight computational budgets, making performance dependent on selecting a small, high-quality subset of frames. Existing frame sampling strategies, such as uniform or fixed-budget selection, fail to adapt to variations in content density or task complexity. To address this, we present FrameOracle, a lightweight, plug-and-play module that predicts both (1) which frames are most relevant to a given query and (2) how many frames are needed. FrameOracle is trained via a curriculum that progresses from weak proxy signals, such as cross-modal similarity, to stronger supervision with FrameOracle-41K, the first large-scale VideoQA dataset with validated keyframe annotations specifying minimal sufficient frames per question. Extensive experiments across five VLMs and six benchmarks show that FrameOracle reduces 16-frame inputs to an average of 10.4 frames without accuracy loss. When starting from 64-frame candidates, it reduces inputs to 13.9 frames on average while improving accuracy by 1.5%, achieving state-of-the-art efficiency–accuracy trade-offs for scalable video understanding.

Deep Learning · Large Language Models

Yoonjeon Kim, Doohyuk Jang, Eunho Yang

Recent research on reasoning models explores the meta-awareness of language models, including their ability to determine optimal thinking duration, recognize knowledge boundaries, and structure concept-level thinking. While current large reasoning models depend solely on answer-based verification, we show that adding meta-awareness objectives leads to significant performance gains over models without such meta-knowledge. **MAPR** utilizes a self-generated task of predicting rollout statistics - specifically length, pass-rate, and concepts used - allowing for verification against the actual statistics. Furthermore, by leveraging this self-predictive capability, the model can regulate its reasoning behavior by i) filtering out trivial or unsolvable prompts, ii) reducing lengthy generations that tend to be incorrect, and iii) generating hints relevant to the problem. The results are inspiring: **MAPR** yields significant improvements in both accuracy and training efficiency on various reasoning benchmarks. More specifically, our method can speed up GRPO training by over 1.28$\times$ to reach the same performance, and achieve 83.18\% gain in accuracy on AIME25, and a 13.04\% average gain over six mathematics benchmarks.

Deep Learning · Foundation Models

Zhengyang Hu, Yanzhi Chen, Hanxiang Ren, Qunsong Zeng, Youyi Zheng, Adrian Weller, Kaibin Huang, Yanchao Yang

Measuring statistical dependency between high-dimensional random variables is a fundamental task in data science and machine learning. Neural mutual information (MI) estimators offer a promising avenue, but they typically require costly test-time training for each new dataset, making them impractical for real-time applications. We present InfoAtlas, a foundation model-like architecture that eliminates this bottleneck by directly inferring MI in a single forward pass. Pretrained on large-scale synthetic data with rich dependence patterns, InfoAtlas learns to identify diverse dependence structures and predict MI directly from the dataset. Comprehensive experiments demonstrate that InfoAtlas matches state-of-the-art neural estimators in accuracy while achieving 100× speedup, can flexibly handle varying dimensions and sample sizes through a single unified model, and generalizes effectively to complex, real-world scenarios. By reformulating MI estimation from an optimization problem to an inference task, InfoAtlas establishes a foundation for real-time dependency analysis.

Deep Learning · Foundation Models

Aleksandr Medvedev, Karthik Viswanathan, Praveenkumar Kanithi, Kirill Vishniakov, Prateek Munjal, Clement Christophe, Tiago Magalhaes, Marco Pimentel, Ronnie Rajan, SHADAB KHAN

Existing genomic foundation models (GFMs) typically treat DNA as raw nucleotide sequences, often overlooking the regulatory context required to interpret genetic variation accurately. We introduce BioToken, a tokenization framework that directly encodes variants and biological annotations into genomic representations, and BioFM, a parameter-efficient model built on this architecture. By leveraging biological inductive biases, BioFM outperforms state-of-the-art models and specialized baselines like Enformer on benchmarks including pathogenicity and expression prediction while requiring 100-fold less compute than current large-scale genomic models. These findings demonstrate that explicitly modeling biological structure yields more robust and efficient genomic representations than scaling alone.

Deep Learning · Large Language Models

Utsav Singh, Sidhaarth Murali, Souradip Chakraborty, Amrit Singh Bedi

Reinforcement learning with verifiable rewards can improve LLM reasoning, but learning is sample-inefficient under sparse terminal rewards. Prior work mitigates this by adding natural language critiques, yet it typically treats critique generation as fixed or auxiliary, so correct-sounding feedback may not translate into higher verified reward. We argue that natural language actor-critic for reasoning is inherently bilevel: the usefulness of the critique is defined by its downstream effect on the actor after adaptation. We formalize this coupling as a Stackelberg bilevel program and derive Bilevel Natural Language Actor-Critic (Bi-NAC), which jointly trains a critic to generate reward-improving feedback and an actor to exploit it. Across reasoning benchmarks, Bi-NAC improves sample and parameter efficiency over RL baselines and fixed-critic feedback methods. We perform experiments on MATH-500, MBPP, and GPQA demonstrating that Bi-NAC significantly enhances parameter and sample efficiency, enabling smaller models to outperform larger baselines. Specifically, our 2B model consistently outperforms the larger 3B GRPO baseline across all tasks (e.g., 46.6% vs. 41.4% on MATH-500), while our 6B model surpasses the 7B GRPO baseline (e.g., 49.3% vs. 43.6% on GPQA). These results show that aligning actor and critic via bilevel formulation provides a robust and efficient alternative for solving complex reasoning tasks.

Deep Learning · Everything Else

Yuting Ma, Lechao Cheng, Xiaohua Xu

Federated Learning (FL) with pre-trained Vision-Language Models (VLMs) has emerged as a promising paradigm for various downstream tasks. By leveraging its strong representations, recent studies improve task adaptation under insufficient local data while preserving generalization. However, these methods emphasize fully local optimization with simple parameter aggregation, which can amplify inter-client optimization inconsistency and intra-client over-specialization under heterogeneous and full-data FL settings, making it difficult to balance global task adaptation and generalization. To address these challenges, we propose FedDTL, a novel federated VLM framework that decouples the image encoder and text encoder across clients and the server. Through decoupled encoder training with server-client modality alignment, FedDTL promotes coherent global semantic update and reduces inter-client optimization inconsistency, improving global task adaptation. To further mitigate intra-client over-specialization, we introduce a two-stage local fine-tuning, where a supervised fine-tuning stage enables rapid and reliable warm-start, followed by a reinforcement learning stage that enhances generalization. Extensive experiments on multiple benchmarks, including label skew and feature shift, demonstrate that FedDTL achieves an effective balance between global task adaptation and generalization under various FL data distributions in both few-shot and full-data regimes.

Deep Learning · Large Language Models

Zihan Su, Hongyang Wei, Kangrui Cen, Yong Wang, Guanhua CHEN, Chun Yuan, Xiangxiang Chu

Unified Multimodal Models (UMMs) integrate both visual understanding and generation within a single framework. Their ultimate aspiration is to create a cycle where understanding and generation mutually reinforce each other. While recent post-training methods have successfully leveraged understanding to enhance generation, the reverse direction of utilizing generation to improve understanding remains largely unexplored. In this work, we propose UniMRG (Unified Multi-Representation Generation), a simple yet effective architecture-agnostic post-training method. UniMRG enhances the understanding capabilities of UMMs by incorporating auxiliary generation tasks. Specifically, we train UMMs to generate multiple intrinsic representations of input images, namely pixel (reconstruction), depth (geometry), and segmentation (structure), alongside standard visual understanding objectives. By synthesizing these diverse representations, UMMs capture rich complementary information regarding appearance, spatial relations, and structural layout. Consequently, UMMs develop a deeper and more comprehensive understanding of visual inputs. Extensive experiments across diverse UMM architectures demonstrate that our method notably enhances fine-grained perception, reduces hallucinations, and improves spatial understanding, while simultaneously boosting generation capabilities.

Social Aspects · Accountability, Transparency, and Interpretability

Yehonatan Elisha, Oren Barkan, Ziv Haddad, Noam Koenigstein

Many visual explanation methods in computer vision highlight pixel importance but struggle to link these low-level cues to semantically meaningful concepts, limiting their interpretability and trustworthiness. We introduce Concept-based Explanations (ConEx), a novel framework that bridges saliency visualization with concept-based reasoning to provide both localized and global interpretability. ConEx automatically discovers class-specific concepts and represents them through concept activation vectors (CAVs), learned without manual supervision using an architecture-specific masking mechanism that reduces noise introduced by the segmentation masks to enhance concept purity. Locally, ConEx generates saliency maps that reveal where each concept appears in the image and how it contributes to the prediction; globally, it identifies the most influential concepts for each class. To evaluate the reliability of these learned concepts, we propose two complementary metrics, Vector-Concept Match (VCM) and Concept-Class Match (CCM), that quantify concept alignment and enable direct comparison with existing methods. Extensive experiments across diverse datasets and architectures demonstrate that ConEx achieves state-of-the-art performance on faithfulness, segmentation, and concept-quality benchmarks. Human studies further confirm that the discovered concepts are interpretable, distinctive, and aligned with human understanding. Overall, ConEx advances the field toward truly interpretable and concept-grounded explanations in vision models.

Deep Learning · Foundation Models

Hyeontaek Hwang, DINH SON NGUYEN, Daeyoung Kim

Fine-tuning Multimodal Large Language Models (MLLMs) on task-specific data is an effective way to improve performance on downstream applications. However, such adaptation often leads to a degradation in generalization on pretrained tasks, a phenomenon known as Catastrophic Forgetting. Existing methods that aim to mitigate this issue either become ineffective when fine-tuning deeper layers of the language decoder or scale poorly with increasing model size. To address these limitations, we propose Model-Dowser, a novel sparse fine-tuning approach for MLLMs. Model-Dowser measures a principled importance score for each model parameter with respect to pretrained generalization (prior to downstream adaptation) by jointly considering weight magnitudes, input activations, and output sensitivities. During fine-tuning, Model-Dowser selectively preserves high-importance parameters and updates the remaining. Comprehensive experiments on two representative MLLMs, LLaVA and NVILA, demonstrate that Model-Dowser effectively mitigates catastrophic forgetting and consistently outperforms prior methods, while remaining resource-efficient and scalable to multi-billion-parameter models.

Applications · Everything Else

Yingming Pu, Tao LIN, Hongyu Chen

Large Language Model (LLM)-based scientific agents have accelerated scientific discovery, yet they often suffer from significant inefficiencies due to adherence to fixed initial priors. Existing approaches predominantly operate within a static hypothesis space, which restricts the discovery of novel phenomena, resulting in computational waste when baseline theories fail. To address this, we propose shifting the focus from searching hypotheses to evolving the underlying scientific principles. We present $\textbf{PiEvo}$, a principle-evolvable framework that treats scientific discovery as Bayesian optimization over an expanding principle space. By integrating Information-Directed Hypothesis Selection via Gaussian Process and an anomaly-driven augmentation mechanism, PiEvo enables agents to autonomously refine their theoretical worldview. Evaluation across four benchmarks demonstrates that PiEvo (1) achieves an average solution quality of up to 90.81\%$\sim$93.15\%, representing a 29.7\%$\sim$31.1\% improvement over the state-of-the-art, (2) attains an 83.3\% speedup in convergence step via significantly reduced sample complexity by optimizing the compact principle space, and (3) maintains robust performance across diverse scientific domains and LLM backbones.

Social Aspects · Accountability, Transparency, and Interpretability

Berkant Turan, Suhrab Asadulla, David Steinmann, Kristian Kersting, Wolfgang Stammer, Sebastian Pokutta

While *Prover-Verifier Games* (PVGs) offer a promising path toward verifiability in nonlinear classification models, they have not yet been applied to complex inputs such as high-dimensional images. Conversely, expressive *concept encodings* effectively allow to translate such data into interpretable concepts but are often utilised in the context of low-capacity linear predictors. In this work, we push towards real-world verifiability by combining the strengths of both approaches. We introduce *Neural Concept Verifier (NCV)*, a unified framework combining PVGs for formal verifiability with concept encodings to handle complex, high-dimensional inputs in an interpretable way. NCV achieves this by utilizing recent minimally supervised concept discovery models to extract structured concept encodings from raw inputs. A *prover* then selects a subset of these encodings, which a *verifier*, implemented as a nonlinear predictor, uses exclusively for decision-making. Our evaluations show that NCV outperforms classic concept-based models and pixel-based PVG classifier baselines on high-dimensional, logically complex datasets and helps mitigate shortcut behavior. Overall, we demonstrate NCV as a promising step toward concept-level, verifiable AI.

Deep Learning · Large Language Models

Linzheng Chai, Jian Yang, Shukai Liu, Wei Zhang, Liran WANG, JinKe, Tao Sun, Congnan Liu, Chenchen Zhang, Hualei Zhu 等

In modern software development, particularly in emerging ``vibe coding'' paradigms, project implementation increasingly begins with visual interactions between users and AI coding assistants, where system architectures are communicated through visual designs before coding. This visual-first approach necessitates AI systems capable of interpreting diagrams across multiple programming languages. However, the development of such systems is severely hindered by the lack of large-scale multimodal training data and evaluation benchmarks. To address these limitations, we present M2C-INSTRUCT, a comprehensive multilingual multimodal instruction-tuning dataset containing over 13.1M samples across 50+ programming languages, designed for visual understanding and diagram interpretation in code generation tasks. We validate our dataset by training M2-CODER, a multilingual multimodal software developer that successfully integrates visual design inputs with textual instructions. We also introduce M2EVAL, a novel multilingual evaluation benchmark for multimodal code generation performance. Experiments show our 7B M2-CODER performs on par with much larger 70B+ models, confirming the quality and effectiveness of our M2C-INSTRUCT. Together, M2C-INSTRUCT, M2-CODER, and M2EVAL provide essential infrastructure for visual-assisted programming in vibe-coding and visual-interactive development workflows.

Deep Learning · Large Language Models

Yiran Wu, Jiale Liu, Jieyu Zhang, Yaolun Zhang, Shilong Liu, Chi Wang, Mengdi Wang, Huazheng Wang, Qingyun Wu

Large language models (LLMs) are increasingly deployed as digital agents that perform multi-step digital work on a computer, but the environments in which they operate remain fragmented and task-specific. Our position is that digital agents need Agent-Native Computer: interfaces that expose system capabilities through compositional observation and action spaces aligned with LLM strengths. To ground this position, we showcase AgentVM, an environment running on top of a modern operating system, which integrates Graphical User Interface (GUI)-based and text-based interactions over a shared system state, and factors interaction into modular environment views. Through quantitative and qualitative analysis, we show that a unified agent-native computer is essential for building general-purpose digital agents.

General Machine Learning · Scalable Algorithms

Felix X.-F. Ye, Xingjie Li, An Yu, Ming-Ching Chang, LINSONG CHU, Davis Wertheimer

Entropic optimal transport (EOT) via Sinkhorn iterations is widely used in modern machine learning, yet GPU solvers remain inefficient at scale. Tensorized implementations suffer quadratic HBM traffic from dense $n\times m$ interactions, while existing online backends avoid storing dense matrices but still rely on generic tiled map-reduce reduction kernels with limited fusion. We present **FlashSinkhorn**, an IO-aware EOT solver for squared Euclidean cost that rewrites stabilized log-domain Sinkhorn updates as row-wise LogSumExp reductions of biased dot-product scores, the same normalization as transformer attention. This enables FlashAttention-style fusion and tiling: fused Triton kernels stream tiles through on-chip SRAM and update dual potentials in a single pass, substantially reducing HBM IO per iteration while retaining linear-memory operations. We further provide streaming kernels for transport application, enabling scalable first- and second-order optimization. On A100 GPUs, FlashSinkhorn achieves up to $32\times$ forward-pass and $161\times$ end-to-end speedups over state-of-the-art online baselines on point-cloud OT, improves scalability on OT-based downstream tasks.

Applications · Robotics

Junhao Shi, Siyin Wang, Xiaopeng Yu, Li Ji, Jingjing Gong, Xipeng Qiu

Vision-Language-Action (VLA) models are bottlenecked by the scarcity of expert demonstrations—expensive triplets of observations, language instructions, and actions. We propose that learning ''how to move'' can be decoupled from learning ''what to do,'' and that the former requires no task labels at all. Our two-stage framework, **Task-Agnostic Pretraining (TAP)** first pre-trains on abundant, cheap *task-agnostic* data (discarded off-task trajectories or autonomous robot play) using an Inverse Dynamics objective that predicts actions from consecutive observations. This self-supervised phase instills physical affordances—grasping, contact dynamics, end-effector control—without human annotation. A lightweight second stage then aligns these physical priors with language instructions using minimal expert data. On the SIMPLER benchmark, our approach matches models trained on 1M+ expert trajectories while using orders of magnitude less labeled data, achieving a 10\% absolute gain over standard behavior cloning. In real-world WidowX experiments, it surpasses internet-scale baselines under visual distribution shifts (e.g., 25\% vs. 0\% under camera perturbations), demonstrating that task-agnostic pretraining yields robust, transferable physical representations for Embodied AI.

Deep Learning · Generative Models and Autoencoders

Jinyan Ye, Zhongjie Duan, Zhiwen Li, Cen Chen, Daoyuan Chen, Yaliang Li, Yingda Chen

Inference-time scaling offers a versatile paradigm for aligning visual generative models with downstream objectives without parameter updates. However, existing approaches that optimize the high-dimensional initial noise suffer from severe inefficiency, as many search directions exert negligible influence on the final generation. We show that this inefficiency is closely related to a spectral bias in generative dynamics: model sensitivity to initial perturbations diminishes rapidly as frequency increases. Building on this insight, we propose Spectral Evolution Search (SES), a plug-and-play framework for initial noise optimization that executes gradient-free evolutionary search within a low-frequency subspace. Theoretically, we derive the Spectral Scaling Prediction from perturbation propagation dynamics, which explains the systematic differences in the impact of perturbations across frequencies. Extensive experiments demonstrate that SES significantly advances the Pareto frontier of generation quality versus computational cost, consistently outperforming strong baselines under equivalent budgets. Our code is available at \url{https://anonymous.4open.science/r/Spectral-Evolution-Search-66DB}.

Deep Learning · Large Language Models

Gengsheng Li, Jinghan He, Shijie Wang, Dan Zhang, Ruiqi Liu, Renrui Zhang, Zijun Yao, Junfeng Fang, Haiyun Guo, Jinqiao Wang

Self-play bootstraps LLM reasoning through an iterative Challenger–Solver loop: the Challenger is trained to generate questions that target the Solver's capabilities, and the Solver is optimized on the generated data to expand its reasoning skills. However, existing frameworks like R-Zero often exhibit non-sustained improvement, where early gains degrade as self-play continues. We identify a key failure mode, Diversity Illusion, where the Solver's training signals appear diverse yet collapse into recurring underlying patterns. It manifests as (1) Local Diversity Illusion, where diversity is enforced only within-batch, inducing cross-iteration mode cycling; and (2) Surface Diversity Illusion, where questions vary superficially but require near-identical reasoning skills. To mitigate them, we propose R-Diverse with two aligned innovations: Memory-Augmented Penalty (MAP), which uses a persistent memory bank to discourage recycling across iterations, and Skill-Aware Measurement (SAM), which evaluates diversity by the reasoning skills exercised rather than surface variation of questions. Across 10 math and general reasoning benchmarks, R-Diverse sustains gains over more iterations and consistently outperforms prior self-play methods.

Deep Learning · Large Language Models

Tomás Vergara Browne, Darshan Patil, Ivan Titov, Siva Reddy, Tiago Pimentel, Marius Mosbach

The superficial alignment hypothesis (SAH) posits that large language models learn most of their knowledge during pre-training, and that post-training merely surfaces this knowledge. The SAH, however, lacks a precise definition, which has led to (i) different and seemingly orthogonal arguments supporting it, and (ii) important critiques to it. We propose a new metric called **Task Complexity**: the length of the shortest program that achieves a target performance on a task. In this framework, the SAH claims that pre-trained models drastically reduce the task complexity of achieving high performance on many tasks. Our definition unifies prior arguments supporting the SAH, interpreting them as different strategies to find such short programs. Experimentally, we estimate task complexities of mathematical reasoning, machine translation, and instruction following tasks and show that their respective task complexities can be remarkably low when conditioned on a pre-trained model. Further, we find that pre-training enables access to strong performances on our tasks, but it can require programs of gigabytes of length to access them. Post-training, on the other hand, collapses the complexity of reaching this same performance by several orders of magnitude. Overall, our results highlight that task adaptation can require remarkably little information—often just a few kilobytes.

Deep Learning · Large Language Models

HyunJin Kim, Jaejun Shim, Young Jin Kim, JinYeong Bak

Unsupervised dense retrievers offer scalability by learning semantic similarity from unlabeled documents via contrastive learning, but they struggle to capture the temporal relevance, retrieving semantically related but temporally misaligned documents-an important aspect when a document collection spans multiple time periods (e.g., retrieving from related document spanning 2018-2025 given a query "Who is the president in 2019?'' introduces temporal ambiguity). Existing methods rely on supervised training with explicit timestamps, which are not always feasible.We propose TPOUR (*Temporal Preference Optimization for Unsupervised Retriever*), which integrates our novel training method *Temporal Retrieval Preference Optimization* (TRPO). TRPO reinterprets preference learning in the temporal dimension, guiding the retriever to favor temporally aligned documents. TPOUR further generalizes to unseen time periods via interpolation in a learned time embedding, enabling continuous temporal alignment. Experiments on temporal QA with a mixed-timestamp document collection show that TPOUR outperforms both unsupervised and supervised baselines. Compared to Nomic Embed v2 MoE, TPOUR Contriever improves nDCG@5 by +7.13 (+23.5%) on explicit and +7.76 (+25.5%) on implicit queries on average.

Theory · Reinforcement Learning and Planning

Jose Aguilar Escamilla, Haoyang Hong, Jiawei Li, Haoyu Zhao, Xuezhou Zhang, Sanghyun Hong, Huazheng Wang

We study reward poisoning attacks in reinforcement learning (RL), where an adversary manipulates rewards within constrained budgets to force the target RL agent to adopt a policy that aligns with the attacker's objectives. Prior works on reward poisoning mainly focused on sufficient conditions to design a successful attacker, while only a few studies discussed the infeasibility of targeted attacks. This paper provides the first precise necessity and sufficiency characterization of the attackability of a linear MDP under reward poisoning attacks. Our characterization draws a bright line between the vulnerable RL instances, and the intrinsically robust ones which cannot be attacked without large costs even running vanilla non-robust RL algorithms. Our theory extends beyond linear MDPs---by approximating deep RL environments as linear MDPs, we show that our theoretical framework effectively distinguishes the attackability and efficiently attacks the vulnerable ones, demonstrating both the theoretical and practical significance of our characterization.