论文检索

Deep Learning · Algorithms

Houyi Li, Ka Man Lo, Shijie Xuyang, Ziqi Wang, Wenzhen Zheng, Haocheng Zhang, Zhao Li, Shuigeng Zhou, Xiangyu Zhang, Daxin Jiang

Mixture-of-Experts (MoE) language models dramatically expand model capacity and achieve remarkable performance without increasing per-token compute. However, can MoEs surpass dense architectures under strictly equal resource constraints — that is, when the total parameter count, training compute, and data budget are identical? This question remains under-explored despite its significant practical value and potential. In this paper, we propose a novel perspective and methodological framework to study this question thoroughly. First, we comprehensively investigate the architecture of MoEs and achieve an optimal model design that maximizes the performance. Based on this, we subsequently find that an MoE model with activation rate in an optimal region is able to outperform its dense counterpart under the same total parameter, training compute and data resource. More importantly, this optimal region remains consistent across different model sizes. Although additional amount of data turns out to be a trade-off for enhanced performance, we show that this can be resolved via reusing data. We validate our findings through extensive experiments, training nearly 200 language models at 2B scale and over 50 at 7B scale, cumulatively processing 50 trillion tokens. All code and models will be released publicly.

Computer Vision · Vision Models & Multimodal

Longrong Yang, Zhixiong Zeng, Yufeng Zhong, Jing Huang, Liming Zheng, Lei Chen, Haibo Qiu, Zequn Qin, Lin Ma, Xi Li

Multimodal large language models are progressively advancing toward multimodal agents that can proactively execute tasks. Existing research on multimodal agents primarily targets either GUI or embodied scenarios, corresponding to interactions within 2D virtual world and 3D physical world, respectively. However, many real-world tasks inherently require agents to interleave interactions across both types of environments. We initially mix GUI and embodied data to train models, but find performance degradation caused by data conflicts. Further analysis reveals that GUI and embodied data exhibit synergy at shallow layers but conflict at deep layers, resembling the cerebrum-cerebellum mechanism in the human brain. To this end, we introduce a high-performance generalist agent, OmniActor, designed from both structural and data perspectives. First, we propose Layer-heterogeneous MoE that separates parameters at deep layers to eliminate conflict, while sharing parameters at shallow layers to leverage synergy. This design enables OmniActor to outperform agents trained solely on GUI or embodied data in their respective tasks. Furthermore, we unify the action spaces of GUI and embodied tasks and collect large-scale datasets from diverse sources for training. This substantially enhances the performance of OmniActor across various scenarios, especially in GUI tasks.

Applications · Neuroscience, Cognitive Science

Zhanglu Yan, Jiayi Mao, Qianhui Liu, Fanfan Li, Tao Luo, Gang Pan, Bowen Zhu, Weng-Fai Wong

Spiking neural networks (SNNs) promise high energy efficiency, particularly with time-to-first-spike (TTFS) encoding, which maximizes sparsity by emitting at most one spike per neuron. However, this energy advantage is often unrealized because inference requires evaluating a temporal decay function and then multiplying the result by the synaptic weights. This paper challenges this costly approach by repurposing a physical hardware `bug', namely, the natural signal decay in optoelectronic devices, as the core computation of TTFS. We fabricated a custom indium oxide optoelectronic synapse that demonstrates how its intrinsic physical decay directly implements the required temporal function. By treating the device's analog output as the fused product of the synaptic weight and temporal decay, optoelectronic synaptic TTFS (named Otters) eliminates these expensive digital operations. To use the Otters' paradigm in complex architectures such as the transformer, which are challenging to train directly due to sparsity, we introduce a novel quantized neural network-to-SNN conversion algorithm. This complete hardware-software co-design enables our model to achieve state-of-the-art accuracy across seven GLUE benchmark datasets and demonstrates a 1.77$\times$ improvement in energy efficiency over previous leading SNNs, based on a comprehensive analysis of compute, data movement, and memory access costs using energy measurements from a commercial 22nm process. Our work thus establishes a new paradigm for energy-efficient SNNs that translates fundamental device physics directly into powerful computational primitives. All codes and data are open source.

Applications · Language, Speech and Dialog

Kaicheng Wang, Liyan Huang, Weike Fang, Weihang Wang

Efficient code retrieval is critical for developer productivity, yet existing benchmarks largely focus on Python and rarely stress-test robustness beyond superficial lexical cues. To address the gap, we introduce an automated pipeline for code search datasets and present CLARC, a C/C++ benchmark built from real-world GitHub repositories. CLARC contains 1,245 query-code pairs for evaluation and 5,472 pairs for training. The benchmark incorporates LLM-generated natural language queries validated through rigorous human scoring and hypothesis testing. To analyze contextual requirements effectively, our pipeline starts by ensuring code compilability. It then categorizes code snippets by dependency complexity, distinguishing whether the code relies on custom-defined types or helper functions. The pipeline also enables CLARC to stress-test retrieval robustness by introducing challenging settings, including identifier anonymization and compilation to low-level languages like Assembly and WebAssembly. Under these conditions, our evaluation of six state-of-the-art models reveals sharp drops in retrieval effectiveness. The experimental results highlight the models' persistent reliance on lexical features rather than code semantic understanding. Our dataset is publicly available at https://huggingface.co/datasets/ClarcTeam/CLARC.

Deep Learning · Everything Else

Paulius Rauba, Mihaela van der Schaar

Large neural networks are typically trained for a fixed computational budget, creating a rigid trade-off between performance and efficiency that is ill-suited for deployment in resource-constrained or dynamic environments. Existing approaches to this problem present a difficult choice: training a discrete collection of specialist models is computationally prohibitive, while dynamic methods like slimmable networks often lack the flexibility to be applied to large, pre-trained foundation models. In this work, we propose *Nested Subspace Networks (NSNs)*, a novel architectural paradigm that enables a single model to be dynamically and granularly adjusted across a continuous spectrum of compute budgets at inference time. The core of our approach is to re-parameterize linear layers to satisfy a nested subspace property, such that the function computed at a given rank is a strict subspace of the function at any higher rank. We show that this entire hierarchy of models can be optimized jointly via an uncertainty-aware objective that learns to balance the contributions of different ranks based on their intrinsic difficulty. We demonstrate empirically that NSNs can be surgically applied to pre-trained LLMs and unlock a smooth and predictable compute-performance frontier. For example, a single NSN-adapted model can achieve a 50\% reduction in inference FLOPs with only a 5 percentage point loss in accuracy. Our findings establish NSNs as a powerful framework for creating the next generation of adaptive foundation models.

Computer Vision · Image and Video Generation

Jianzong Wu, Liang Hou, Haotian Yang, Ye Tian, Pengfei Wan, Di ZHANG, Yunhai Tong

The quadratic complexity of full attention mechanisms poses a significant bottleneck for Video Diffusion Models (VDMs) aiming to generate long-duration, high-resolution videos. While various sparse attention methods have been proposed, many are designed as training-free inference accelerators or do not optimally capture the unique spatio-temporal characteristics inherent in video data when trained natively. This paper introduces Video Mixture of Block Attention (VMoBA), a novel sparse attention mechanism specifically adapted for VDMs. Motivated by an in-depth analysis of attention patterns within pre-trained video transformers, which revealed strong spatio-temporal locality, varying query importance, and head-specific concentration levels, VMoBA enhances the original MoBA framework with three key modifications: (1) a layer-wise recurrent block partition scheme (1D-2D-3D) to dynamically adapt to diverse spatio-temporal attention patterns and improve efficiency; (2) global block selection to prioritize the most salient query-key block interactions across an entire attention head; and (3) threshold-based block selection to dynamically determine the number of attended blocks based on their cumulative similarity. Extensive experiments demonstrate that VMoBA significantly accelerates the training of VDMs on longer sequences, achieving 2.92$\times$ FLOPs and 1.48$\times$ latency speedup, while attaining comparable or even superior generation quality to full attention. Furthermore, VMoBA exhibits competitive performance in training-free inference, offering 2.40$\times$ FLOPs and 1.35$\times$ latency speedup for high-res video generation.

Fan Zhang, Zebang Cheng, Chong Deng, Haoxuan Li, Zheng Lian, Qian Chen, Huadai Liu, Wen Wang, YiFan Zhang, Renrui Zhang 等

Recent advances in multimodal large language models (MLLMs) have catalyzed transformative progress in affective computing, enabling models to exhibit emergent emotional intelligence. Despite substantial methodological progress, current emotional benchmarks remain limited, as it is still unknown: (a) the generalization abilities of MLLMs across distinct scenarios, and (b) their reasoning capabilities to identify the triggering factors behind emotional states. To bridge these gaps, we present MME-Emotion, a systematic benchmark that assesses both emotional understanding and reasoning capabilities of MLLMs, enjoying scalable capacity, diverse settings, and unified protocols. As the largest emotional intelligence benchmark for MLLMs, MME-Emotion contains over 6,000 curated video clips with task-specific questioning-answering (QA) pairs, spanning broad scenarios to formulate eight emotional tasks. It further incorporates a holistic evaluation suite with hybrid metrics for emotion recognition and reasoning, analyzed through a multi-agent system framework. Through a rigorous evaluation of 20 advanced MLLMs, we uncover both their strengths and limitations, yielding several key insights: (1) Current MLLMs exhibit unsatisfactory emotional intelligence, with the best-performing model achieving only $39.3\%$ recognition score and $56.0\%$ Chain-of-Thought (CoT) score on our benchmark. (2) Generalist models (\emph{e.g.}, Gemini-2.5-Pro) derive emotional intelligence from generalized multimodal understanding capabilities, while specialist models (\emph{e.g.}, R1-Omni) can achieve comparable performance through domain-specific post-training adaptation. By introducing MME-Emotion, we hope that it can serve as a foundation for advancing MLLMs' emotional intelligence in the future.

Deep Learning · Graph Neural Networks

Yisen Gao, Jiaxin Bai, Tianshi Zheng, Ziwei Zhang, Qingyun Sun, Xingcheng Fu, Jianxin Li, Yangqiu Song

Abductive reasoning in knowledge graphs aims to generate plausible logical hypotheses from observed entities, with broad applications in areas such as clinical diagnosis and scientific discovery. However, due to a lack of controllability, a single observation may yield numerous plausible but redundant or irrelevant hypotheses on large-scale knowledge graphs. To address this limitation, we introduce the task of controllable hypothesis generation to improve the practical utility of abductive reasoning. This task faces two key challenges when controlling for generating long and complex logical hypotheses: hypothesis space collapse and hypothesis reward oversensitivity. To address these challenges, we propose **CtrlHGen**, a **C**on**tr**ollable **l**ogcial **H**ypothesis **Gen**eration framework for abductive reasoning over knowledge graphs, trained in a two-stage paradigm including supervised learning and subsequent reinforcement learning. To mitigate hypothesis space collapse, we design a dataset augmentation strategy based on sub-logical decomposition, enabling the model to learn complex logical structures by leveraging semantic patterns in simpler components. To address hypothesis reward oversensitivity, we incorporate smoothed semantic rewards including Dice and Overlap scores, and introduce a condition-adherence reward to guide the generation toward user-specified control constraints. Extensive experiments on three benchmark datasets demonstrate that our model not only better adheres to control conditions but also achieves superior semantic similarity performance compared to baselines. Our code is available at https://github.com/HKUST-KnowComp/CtrlHGen.

Reinforcement Learning · Planning

Narjes Nourzad, Carlee Joe-Wong

Reinforcement learning (RL) agents often face high sample complexity in sparse or delayed reward settings, due to limited prior knowledge. Conversely, large language models (LLMs) can provide subgoal structures, plausible trajectories, and abstract priors that support early learning. Yet heavy reliance on LLMs introduces scalability issues and risks dependence on unreliable signals, motivating ongoing efforts to integrate LLM guidance without compromising RL’s autonomy. We propose MIRA (Memory-Integrated Reinforcement Learning Agent), which incorporates a structured, evolving memory graph to guide early learning. This graph stores decision-relevant information, such as trajectory segments and subgoal decompositions, and is co-constructed from the agent’s high-return experiences and LLM outputs, amortizing LLM queries into a persistent memory instead of relying on continuous real-time supervision. From this structure, we derive a utility signal that softly adjusts advantage estimation to refine policy updates without altering the underlying reward function. As training progresses, the agent’s policy surpasses the initial LLM-derived priors, and the utility term decays, leaving long-term convergence guarantees intact. We show theoretically that this utility-based shaping improves early-stage learning in sparse-reward settings. Empirically, MIRA outperforms RL baselines and reaches returns comparable to methods that rely on frequent LLM supervision, while requiring substantially fewer online LLM queries.

Reinforcement Learning · Deep RL

Mingyu Su, Jian Guan, Yuxian Gu, Minlie Huang, Hongning Wang

Post-training methods, especially Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL), play an important role in improving large language models' (LLMs) complex reasoning abilities. However, the dominant two-stage pipeline (SFT then RL) suffers from a key inconsistency: SFT enforces rigid imitation that suppresses exploration and induces forgetting, limiting RL's potential for improvements. We address this inefficiency with TRAPO (**T**rust-**R**egion **A**daptive **P**olicy **O**ptimization), a hybrid framework that interleaves SFT and RL within each training instance by optimizing SFT loss on expert prefixes and RL loss on the model's own completions, unifying external supervision and self-exploration. To stabilize training, we introduce Trust-Region SFT (TrSFT), which minimizes forward KL divergence inside a trust region but attenuates optimization outside, effectively shifting toward reverse KL and yielding stable, mode-seeking updates favorable for RL. An adaptive prefix-selection mechanism further allocates expert guidance based on measured utility. Experiments on five mathematical reasoning benchmarks show that TRAPO consistently surpasses standard SFT, RL, and SFT-then-RL pipelines, as well as recent state-of-the-art approaches, establishing a strong new paradigm for reasoning-enhanced LLMs.

Loka Li, Wong Kang, Minghao Fu, Guangyi Chen, Zhenhao Chen, Gongxu Luo, Yuewen Sun, Salman Khan, Peter Spirtes, Kun Zhang

Understanding human behavior traits is central to applications in human-computer interaction, computational social science, and personalized AI systems. Such understanding often requires integrating multiple modalities to capture nuanced patterns and relationships. However, existing resources rarely provide datasets that combine behavioral descriptors with complementary modalities such as facial attributes and biographical information. To address this gap, we present PersonaX, a curated collection of multimodal datasets designed to enable comprehensive analysis of public traits across modalities. PersonaX consists of (1) CelebPersona, featuring 9444 public figures from diverse occupations, and (2) AthlePersona, covering 4181 professional athletes across 7 major sports leagues. Each dataset includes behavioral trait assessments inferred by three high-performing large language models, alongside facial imagery and structured biographical features. We analyze PersonaX at two complementary levels. First, we abstract high-level trait scores from text descriptions and apply five statistical independence tests to examine their relationships with other modalities. Second, we introduce a novel causal representation learning (CRL) framework tailored to multimodal and multi-measurement data, providing theoretical identifiability guarantees. Experiments on both synthetic and real-world data demonstrate the effectiveness of our approach. By unifying structured and unstructured analysis, PersonaX establishes a foundation for studying LLM-inferred behavioral traits in conjunction with visual and biographical attributes, advancing multimodal trait analysis and causal reasoning. The code is available at https://github.com/lokali/PersonaX.

Reinforcement Learning · Online

Zhibo Hou, Zhiyu An, Wan Du

When there exists an unlearnable source of randomness (noisy-TV) in the environment, a naively intrinsic reward driven exploring agent gets stuck at that source of randomness and fails at exploration. Intrinsic reward based on uncertainty estimation or distribution similarity, while eventually escapes noisy-TVs as time unfolds, suffers from poor sample efficiency and high computational cost. Inspired by recent findings from neuroscience that humans monitor their improvements during exploration, we propose a novel method for intrinsically-motivated exploration, named Learning Progress Monitoring (LPM). During exploration, LPM rewards model improvements instead of prediction error or novelty, effectively rewards the agent for observing learnable transitions rather than the unlearnable transitions. We introduce a dual-network design that uses an error model to predict the expected prediction error of the dynamics model in its previous iteration, and use the difference between the model errors of the current iteration and previous iteration to guide exploration. We theoretically show that the intrinsic reward of LPM is zero-equivariant and a monotone indicator of Information Gain (IG), and that the error model is necessary to achieve monotonicity correspondence with IG. We empirically compared LPM against state-of-the-art baselines in noisy environments based on MNIST, 3D maze with 160x120 RGB inputs, and Atari. Results show that LPM's intrinsic reward converges faster, explores more states in the maze experiment, and achieves higher extrinsic reward in Atari. This conceptually simple approach marks a shift-of-paradigm of noise-robust exploration.

Applications · Physics

Nan Jiang, Ziyi Wang, Yexiang Xue

Symbolic regression seeks to uncover physical laws from experimental data by searching for closed-form expressions, which is an important task in AI-driven scientific discovery. Yet the exponential growth of the search space of expression renders the task computationally challenging. A promising yet underexplored direction for reducing the search space and accelerating training lies in *symbolic equivalence*: many expressions, although syntactically different, define the same function -- for example, $\log(x_1^2x_2^3)$, $\log(x_1^2)+\log(x_2^3)$, and $2\log(x_1)+3\log(x_2)$. Existing algorithms treat such variants as distinct outputs, leading to redundant exploration and slow learning. We introduce EGG-SR, a unified framework that integrates symbolic equivalence into a class of modern symbolic regression methods, including Monte Carlo Tree Search (MCTS), Deep Reinforcement Learning (DRL), and Large Language Models (LLMs). \method-SR compactly represents equivalent expressions through the proposed EGG module (via equality graphs), accelerating learning by: (1) pruning redundant subtree exploration in EGG-MCTS, (2) aggregating rewards across equivalent generated sequences in EGG-DRL, and (3) enriching feedback prompts in EGG-LLM. Theoretically, we show the benefit of embedding EGG into learning: it tightens the regret bound of MCTS and reduces the variance of the DRL gradient estimator. Empirically, EGG-SR consistently enhances a class of symbolic regression models across several benchmarks, discovering more accurate expressions within the same time limit. Project page is at: https://nan-jiang-group.github.io/egg-sr.

Deep Learning · Theory

Noam Razin, Yong Lin, Jiarui Yao, Sanjeev Arora

Reward models are key to language model post-training and inference pipelines. Conveniently, recent work showed that every language model defines an implicit reward model (IM-RM), without requiring any architectural changes. However, such IM-RMs tend to generalize worse, especially out-of-distribution, compared to explicit reward models (EX-RMs) that apply a dedicated linear head over the hidden representations of a language model. The existence of a generalization gap is puzzling, as EX-RMs and IM-RMs are nearly identical. They can be trained using the same data, loss function, and language model, and differ only in how the reward is computed. Toward a fundamental understanding of the implicit biases underlying different reward model types, we investigate the root cause of this gap. Our main finding, backed by theory and experiments, is that IM-RMs rely more heavily on superficial token-level cues. Consequently, they often generalize worse than EX-RMs under token-level distribution shifts, as well as in-distribution. Furthermore, we provide evidence against alternative hypotheses for the generalization gap. Most notably, we challenge the claim that IM-RMs struggle in tasks where generation is harder than verification because they can operate both as a verifier and a generator. Overall, our results highlight that seemingly minor design choices can substantially impact the generalization behavior of reward models.

Computer Vision · Image and Video Generation

Yuran Dong, Hang Dai, Mang Ye

Multimodal editing large models have demonstrated powerful editing capabilities across diverse tasks. However, a persistent and long-standing limitation is the decline in facial identity (ID) consistency during realistic portrait editing. Due to the human eye’s high sensitivity to facial features, such inconsistency significantly hinders the practical deployment of these models. Current facial ID preservation methods struggle to achieve consistent restoration of both facial identity and edited element IP due to Cross-source Distribution Bias and Cross-source Feature Contamination. To address these issues, we propose EditedID, an Alignment-Disentanglement-Entanglement framework for robust identity-specific facial restoration. By systematically analyzing diffusion trajectories, sampler behaviors, and attention properties, we introduce three key components: 1) Adaptive mixing strategy that aligns cross-source latent representations throughout the diffusion process. 2) Hybrid solver that disentangles source-specific identity attributes and details. 3) Attentional gating mechanism that selectively entangles visual elements. Extensive experiments show that EditedID achieves state-of-the-art performance in preserving original facial ID and edited element IP consistency. As a training-free and plug-and-play solution, it establishes a new benchmark for practical and reliable single/multi-person facial identity restoration in open-world settings, paving the way for the deployment of multimodal editing large models in real-person editing scenarios. The code is available at https://github.com/NDYBSNDY/EditedID.

Weilin Zhou

State-of-the-art models for code representation, such as GraphCodeBERT, embed the hierarchical structure of source code into Euclidean space. This approach can lead to significant representation distortion, especially when embedding deep or highly branched hierarchies,limiting the models' ability to capture deep program semantics. We argue that the natural geometry for code is hyperbolic, as its exponential volume growth perfectly matches the tree-like structure of a code's Abstract Syntax Tree (AST), enabling low-distortion hierarchical embeddings. We introduce {HypeCodeNet}, a geometric deep learning framework that operates natively in hyperbolic space. Formulated in the numerically stable Lorentz model, its manifold-aware components include a hyperbolic embedding layer, a tangent space message-passing mechanism, and a geodesic-based attention module. On code clone detection, code completion, and link prediction, HypeCodeNet significantly outperforms existing Euclidean models, especially on tasks requiring deep structural understanding. Our work suggests that hyperbolic geometry offers a geometrically sound foundation for code representation, establishing hyperbolic geometry as a key to unlocking the structured semantics of code.

Computer Vision · Image and Video Generation

Kaiyi Huang, Yukun Huang, Xintao WANG, Zinan Lin, Xuefei Ning, Pengfei Wan, Di ZHANG, Yu Wang, Xihui Liu

Existing AI-based film generation systems can generate high-quality videos, but struggle to design expressive camera language and establish cinematic rhythm. This deficiency leads to templated visuals and unengaging narratives. To address these limitations, we introduce FilMaster, an end-to-end automated film generation system that integrates real-world cinematic principles to generate professional-grade, editable films. Inspired by professional filmmaking, FilMaster is built on two key cinematic principles: (1) camera language design by learning cinematography from extensive real-world film references, and (2) cinematic rhythm by emulating professional post-production workflows. For camera language, our Multi-shot Synergized Camera Language Design module introduces a novel scene-level Retrieval-Augmented Generation (RAG) framework. Unlike shot-level RAG which retrieves references independently and often leads to visual incoherence, our approach treats an entire scene, comprising multiple shots with a shared spatio-temporal context and narrative objective, as a single, unified query. This holistic query retrieves a consistent set of semantically similar shots with cinematic techniques from a large corpus of 440,000 real film clips. These references then guide an LLM to synergistically plan coherent and expressive camera language for all shots within that scene. To achieve cinematic rhythm, our Audience-Aware Cinematic Rhythm Control module emulates professional post-production, featuring a Rough Cut assembly followed by a Fine Cut process that uses simulated audience feedback to optimize the integration of video and sound for cinematic rhythm. Extensive experiments show superior performance in camera language and cinematic rhythm, paving the way for generative AI in professional filmmaking.

General Machine Learning · Representation Learning

Junyi Lin, Dunyao Xue, Jun Yu, Hongteng Xu, Cheng Meng

We introduce SEINT, a novel Special Euclidean group-Invariant (SE(\emph{p})) metric for comparing probability distributions on $p$-dimensional measured Banach spaces. Existing SE(\emph{p})-invariant alignment methods often face high computational costs or lack metric guarantees. To overcome these limitations, we develop a polar transport discrepancy combined with distance convolution to extract SE(\emph{p})-invariant representations. These representations are then used to compute the alignment between two distributions via optimal transport. Theoretically, we prove that SEINT is a well-defined metric on the space of isometry classes of normed vector spaces. Beyond its inherent SE(\emph{p})-invariance, SEINT also supports cross-space distribution comparison. Computationally, SEINT aligns two samples of size $n$ with a complexity of just $\mathcal{O}(n\log n)$ to $\mathcal{O}(n^2)$. Extensive experiments validate its advantages: As a robust metric, it outperforms or matches existing SE(\emph{p})-invariant methods in classification and cross-space tasks under isometries. As a regularizer, it greatly enhances molecular generation performance across both pre-training and fine-tuning tasks, achieving state-of-the-art (SOTA) results on key benchmarks.

Computer Vision · Vision Models & Multimodal

Ziyue Wang, Sheng JIn, ZHONGRONG ZUO, Jiawei Wu, Han Qiu, Qi She, Hao Zhang, Jiang Xudong

Reinforcement learning (RL) has shown strong potential for enhancing reasoning in multimodal large language models (MLLMs), yet existing video reasoning methods often rely on coarse sequence-level rewards or single-factor token selection. Such approaches neglect fine-grained links among visual inputs, temporal dynamics, and linguistic outputs, limiting both accuracy and interpretability. We propose Video-KTR, a modality-aware policy shaping framework that performs selective, token-level RL by combining three attribution signals: (1) visual-aware tokens identified via counterfactual masking to reveal perceptual dependence; (2) temporal-aware tokens detected through frame shuffling to expose causal and temporal sensitivity; and (3) high-entropy tokens signaling predictive uncertainty. By reinforcing only the union of key tokens, Video-KTR focuses learning on semantically informative, modality-sensitive content while filtering out low-value tokens. Across five challenging benchmarks, Video-KTR achieves state-of-the-art or highly competitive results—42.7% on Video-Holmes, surpassing GPT-4o—with consistent gains on both reasoning-centric and general video understanding tasks. Ablation studies verify the complementary roles of the attribution signals and the robustness of targeted token-level updates. Overall, Video-KTR improves accuracy and interpretability, offering a simple, drop-in extension to RL for complex video reasoning.

General Machine Learning · Probabilistic Methods

Zifan Wang, Alice Harting, Matthieu Barreau, Michael Zavlanos, Karl H. Johansson

Guidance of generative models is typically achieved by modifying the probability flow vector field through the addition of a guidance field. In this paper, we instead propose the Source-Guided Flow Matching (SGFM) framework, which modifies the source distribution directly while keeping the pre-trained vector field intact. This reduces the guidance problem to a well-defined problem of sampling from the source distribution. We theoretically show that SGFM recovers the desired target distribution exactly. Furthermore, we provide bounds on the Wasserstein error for the generated distribution when using an approximate sampler of the source distribution and an approximate vector field. The key benefit of our approach is that it allows the user to flexibly choose the sampling method depending on their specific problem. To illustrate this, we systematically compare different sampling methods and discuss conditions for asymptotically exact guidance. Moreover, our framework integrates well with optimal flow matching models since the straight transport map generated by the vector field is preserved. Experimental results on synthetic 2D benchmarks, physics-informed generative tasks, and imaging inverse problems demonstrate the effectiveness and flexibility of the proposed framework.