Related papers: STRIVE: Structured Spatiotemporal Exploration for …
Pre-trained on tremendous image-text pairs, vision-language models like CLIP have demonstrated promising zero-shot generalization across numerous image-based tasks. However, extending these capabilities to video tasks remains challenging…
Despite recent successes, test-time scaling - i.e., dynamically expanding the token budget during inference as needed - remains brittle for vision-language models (VLMs): unstructured chains-of-thought about images entangle perception and…
Spatio-temporal video grounding (STVG) requires localizing a target object in untrimmed videos both temporally and spatially from natural language descriptions. Despite their strong language understanding, multimodal large language models…
Reinforcement Learning with Verifiable Rewards (RLVR) elicits long chain-of-thought reasoning in large language models (LLMs), but outcome-based rewards lead to coarse-grained advantage estimation. While existing approaches improve RLVR via…
Video temporal understanding is crucial for multimodal large language models (MLLMs) to reason over events in videos. Despite recent advances in general video understanding, current MLLMs still struggle with fine-grained temporal reasoning.…
We present STORM (Search-Guided Generative World Models), a novel framework for spatio-temporal reasoning in robotic manipulation that unifies diffusion-based action generation, conditional video prediction, and search-based planning.…
Test-time reinforcement learning mitigates the reliance on annotated data by using majority voting results as pseudo-labels, emerging as a complementary direction to reinforcement learning with verifiable rewards (RLVR) for improving…
Reinforcement Learning with Verifiable Rewards (RLVR) is a powerful paradigm for enhancing the reasoning ability of Large Language Models (LLMs). Yet current RLVR methods often explore poorly, leading to premature convergence and entropy…
Vision-language models (VLMs) have achieved strong multimodal reasoning capabilities, but further improving them still relies heavily on large-scale human-constructed supervision for post-training. Such supervision is costly to obtain,…
Large Reasoning Models (LRMs) with long chain-of-thought capabilities, optimized via reinforcement learning with verifiable rewards (RLVR), excel at objective reasoning tasks like mathematical problem solving and code generation. However,…
Video large language models (Video LLMs) achieve strong benchmark accuracy, yet often answer video questions through shortcuts such as single-frame cues and language priors rather than by tracking spatiotemporal dynamics. This issue is…
Video understanding is inherently intention-driven-humans naturally focus on relevant frames based on their goals. Recent advancements in multimodal large language models (MLLMs) have enabled flexible query-driven reasoning; however,…
Reinforcement learning (RL) has shown strong potential for enhancing reasoning in multimodal large language models, yet existing video reasoning methods often rely on coarse sequence-level rewards or single-factor token selection,…
Existing Multimodal Large Language Models (MLLMs) struggle with 3D spatial reasoning, as they fail to construct structured abstractions of the 3D environment depicted in video inputs. To bridge this gap, drawing inspiration from cognitive…
In this report, we present the winning solution that achieved the 1st place in the Complex Video Reasoning & Robustness Evaluation Challenge 2025. This challenge evaluates the ability to generate accurate natural language answers to…
Class-incremental learning is one of the most important settings for the study of Continual Learning, as it closely resembles real-world application scenarios. With constrained memory sizes, catastrophic forgetting arises as the number of…
Video understanding represents the most challenging frontier in computer vision, requiring models to reason about complex spatiotemporal relationships, long-term dependencies, and multimodal evidence. The recent emergence of Video-Large…
Continual video instance segmentation demands both the plasticity to absorb new object categories and the stability to retain previously learned ones, all while preserving temporal consistency across frames. In this work, we introduce…
Spatial-temporal reasoning is a challenging task in Artificial Intelligence (AI) due to its demanding but unique nature: a theoretic requirement on representing and reasoning based on spatial-temporal knowledge in mind, and an applied…
Recent progress in reinforcement learning with verifiable rewards (RLVR) offers a practical path to self-improvement of language models, but existing methods face a key trade-off: endogenous self-play can drift over iterations, while…