Related papers: CollabVR: Collaborative Video Reasoning with Visio…
Despite significant advances in Vision Language Models (VLMs), they remain constrained by the complexity and redundancy of visual input. When images contain large amounts of irrelevant information, VLMs are susceptible to interference, thus…
Editing complex visual content from ambiguous or partially specified instructions remains a core challenge in vision-language modeling. Existing models can contextualize content but often fail to infer the underlying intent within a…
Effective planning requires strong world models, but high-level world models that can understand and reason about actions with semantic and temporal abstraction remain largely underdeveloped. We introduce the Vision Language World Model…
Recent advances in vision-language models (VLMs) emphasize long chain-of-thought reasoning; yet, we find that their performance on visual tasks is primarily limited by a lack of visual perception as opposed to reasoning itself. In this…
Vision-Language Models (VLMs) excel at visual reasoning but still struggle with integrating external knowledge. Retrieval-Augmented Generation (RAG) is a promising solution, but current methods remain inefficient and often fail to maintain…
Video Question Answering (VideoQA) is a challenging task that requires understanding complex visual and temporal relationships within videos to answer questions accurately. In this work, we introduce \textbf{ReasVQA} (Reasoning-enhanced…
Despite the remarkable success of Vision-Language Models (VLMs), their performance on a range of complex visual tasks is often hindered by a "visual processing bottleneck": a propensity to lose grounding in visual evidence and exhibit a…
We are interested in enabling visual planning for complex long-horizon tasks in the space of generated videos and language, leveraging recent advances in large generative models pretrained on Internet-scale data. To this end, we present…
MLLMs have been widely studied for video question answering recently. However, most existing assessments focus on natural videos, overlooking synthetic videos, such as AI-generated content (AIGC). Meanwhile, some works in video generation…
Despite recent advances in Vision-Language Models (VLMs), long-video understanding remains a challenging problem. Although state-of-the-art long-context VLMs can process around 1000 input frames, they still struggle to effectively leverage…
Vision-language models (VLMs) have shown remarkable advancements in multimodal reasoning tasks. However, they still often generate inaccurate or irrelevant responses due to issues like hallucinated image understandings or unrefined…
Recently, reasoning-based MLLMs have achieved a degree of success in generating long-form textual reasoning chains. However, they still struggle with complex tasks that necessitate dynamic and iterative focusing on and revisiting of visual…
Vision language models (VLMs) have shown remarkable capabilities in integrating linguistic and visual reasoning but remain fundamentally limited in understanding dynamic spatiotemporal interactions. Humans effortlessly track and reason…
While vision-language models (VLMs) have exhibited multi-turn visual reasoning capabilities, their reasoning trajectories remain relatively shallow and are dominated by a text-centric paradigm, limiting their applicability to complex visual…
Video generative models show emerging reasoning behaviors. It is essential to ensure that generated events remain causally consistent across frames for reliable deployment, a property we define as reasoning coherence. To bridge the gap in…
Multimodal Large Language Models (MLLMs) achieve strong multimodal reasoning performance, yet we identify a recurring failure mode in long-form generation: as outputs grow longer, models progressively drift away from image evidence and fall…
Video diffusion models have made rapid progress in perceptual realism and temporal coherence, but they remain primarily optimized for plausible generation rather than verifiable reasoning. This limitation is especially pronounced in tasks…
Process Reward Models (PRMs) provide step-level supervision that improves the reliability of reasoning in large language models. While PRMs have been extensively studied in text-based domains, their extension to Vision Language Models…
Recent breakthroughs in computer vision and natural language processing have spurred interest in challenging multi-modal tasks such as visual question-answering and visual dialogue. For such tasks, one successful approach is to condition…
Large Vision-Language Models (LVLMs) achieve strong performance on visual question answering benchmarks, yet often rely on spurious correlations rather than genuine causal reasoning. Existing evaluations primarily assess the correctness of…