Related papers: VideoSSR: Video Self-Supervised Reinforcement Lear…
Temporal Video Grounding (TVG), which requires pinpointing relevant temporal segments from video based on language query, has always been a highly challenging task in the field of video understanding. Videos often have a larger volume of…
Despite significant breakthroughs in video analysis driven by the rapid development of large multimodal models (LMMs), there remains a lack of a versatile evaluation benchmark to comprehensively assess these models' performance in video…
Large Vision-Language Models (LVLMs) have recently advanced robotic manipulation by leveraging vision for scene perception and language for instruction following. However, existing methods rely heavily on costly human-annotated training…
Multimodal reward models have advanced substantially in text and image domains, yet progress in video understanding reward modeling remains severely limited by the lack of robust evaluation benchmarks and high-quality preference data. To…
Reinforcement learning with verifiable rewards (RLVR) has become a key technique for enhancing large language models (LLMs), with verification engineering playing a central role. However, best practices for RL in instruction following…
The remarkable natural language understanding, reasoning, and generation capabilities of large language models (LLMs) have made them attractive for application to video understanding, utilizing video tokens as contextual input. However,…
Existing Multimodal Large Language Models (MLLMs) often suffer from hallucinations in long video understanding (LVU), primarily due to the imbalance between textual and visual tokens. Observing that MLLMs handle short visual inputs well,…
Recently, researchers have attempted to investigate the capability of LLMs in handling videos and proposed several video LLM models. However, the ability of LLMs to handle video grounding (VG), which is an important time-related video task…
Reinforcement Learning with Verifiable Rewards (RLVR) has been successfully applied to significantly boost the capabilities of pretrained large language models, especially in the math and logic problem domains. However, current research and…
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…
Reinforcement learning is a powerful framework for robots to acquire skills from experience, but often requires a substantial amount of online data collection. As a result, it is difficult to collect sufficiently diverse experiences that…
We present a self-supervised Contrastive Video Representation Learning (CVRL) method to learn spatiotemporal visual representations from unlabeled videos. Our representations are learned using a contrastive loss, where two augmented clips…
Large Multimodal Models (LMMs), or Vision-Language Models (VLMs), have shown impressive capabilities in a wide range of visual tasks. However, they often struggle with fine-grained visual reasoning, failing to identify domain-specific…
Multimodal large language models (MLLMs) have demonstrated remarkable capabilities in vision-language answering tasks. Despite their strengths, these models often encounter challenges in achieving complex reasoning tasks such as…
Vision-language models (VLM) excel at general understanding yet remain weak at dynamic spatial reasoning (DSR), i.e., reasoning about the evolvement of object geometry and relationship in 3D space over time, largely due to the scarcity of…
Reinforcement Fine-Tuning (RFT) with verifiable rewards has advanced large language models but remains underexplored for Vision-Language (VL) models. The Vision-Language Reward Model (VL-RM) is key to aligning VL models by providing…
Current multimodal large language models (MLLMs) struggle with hour-level video understanding, facing significant challenges not only in modeling the substantial information volume of long videos but also in overcoming the memory wall and…
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,…
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…
Video super-resolution (VSR) can achieve better performance compared to single image super-resolution by additionally leveraging temporal information. In particular, the recurrent-based VSR model exploits long-range temporal information…