相关论文: STRIVE: Structured Spatiotemporal Exploration for …

Referring Video Object Segmentation (RVOS) aims to segment target objects in videos based on natural language descriptions. However, fixed keyframe-based approaches that couple a vision language model with a separate propagation module…

Long video understanding is essential for human-like intelligence, enabling coherent perception and reasoning over extended temporal contexts. While the emerging thinking-with-frames paradigm, which alternates between global temporal…

Many video reasoning tasks require tracking motion, temporal order, and evolving visual states across frames. Existing methods built on large vision-language models (LVLMs) often address this challenge by externalizing reasoning through…

Recent advances in large language models (LLMs) have demonstrated that reinforcement learning with verifiable rewards (RLVR) can significantly enhance reasoning abilities by directly optimizing correctness, rather than relying solely on…

Structured, procedural reasoning is essential for Large Language Models (LLMs), especially in mathematics. While post-training methods have improved LLM performance, they still fall short in capturing deep procedural logic on complex tasks.…

Effective modeling of complex spatiotemporal dependencies in long-form videos remains an open problem. The recently proposed Structured State-Space Sequence (S4) model with its linear complexity offers a promising direction in this space.…

Reinforcement learning (RL) has emerged as an effective paradigm for enhancing model reasoning. However, existing RL methods like GRPO typically rely on unstructured self-sampling to fit scalar rewards, often producing inefficient rollouts…

Vision-Language Models (VLMs) have been applied to autonomous driving to support decision-making in complex real-world scenarios. However, their training on static, web-sourced image-text pairs fundamentally limits the precise…

Despite the prosperity of the video language model, the current pursuit of comprehensive video reasoning is thwarted by the inherent spatio-temporal incompleteness within individual videos, resulting in hallucinations and inaccuracies. A…

Value-decomposition methods, which reduce the difficulty of a multi-agent system by decomposing the joint state-action space into local observation-action spaces, have become popular in cooperative multi-agent reinforcement learning (MARL).…

Large Vision-Language Models (LVLMs) have shown exceptional performance in multimodal tasks, but their effectiveness in complex visual reasoning is still constrained, especially when employing Chain-of-Thought prompting techniques. In this…

Most successful self-supervised learning methods are trained to align the representations of two independent views from the data. State-of-the-art methods in video are inspired by image techniques, where these two views are similarly…

Unified video models exhibit strong capabilities in understanding and generation, yet they struggle with reason-informed visual editing even when equipped with powerful internal vision-language models (VLMs). We attribute this gap to two…

To build Video Question Answering (VideoQA) systems capable of assisting humans in daily activities, seeking answers from long-form videos with diverse and complex events is a must. Existing multi-modal VQA models achieve promising…

Multi-video event understanding demands models that can locate and attribute query-relevant evidence scattered across long, heterogeneous video corpora. Existing large vision-language models (LVLMs) often underperform in this regime because…

Recent advancements in reinforcement learning, particularly through Group Relative Policy Optimization (GRPO), have significantly improved multimodal large language models for complex reasoning tasks. However, two critical limitations…

Previous text-guided video editing methods often suffer from temporal inconsistency, motion distortion, and-most notably-limited domain transformation. We attribute these limitations to insufficient modeling of spatiotemporal pixel…

Despite advances in reinforcement learning (RL)-based video reasoning with large language models (LLMs), data collection and fine-tuning remain significant challenges. These methods often rely on large-scale supervised fine-tuning (SFT)…

Large language models can exhibit emergent reasoning behaviors, often manifested as recurring lexical patterns (e.g., "wait," indicating verification). However, complex reasoning trajectories remain sparse in unconstrained sampling, and…

LLM-based equation discovery offers a promising route to recovering symbolic laws from data, but many systems still rely on generation-centered loops that propose candidates, fit parameters, score results, and reuse selected examples. Such…