Related papers: TSPO: Temporal Sampling Policy Optimization for Lo…

Despite progress in multimodal large language models (MLLMs), the challenge of interpreting long-form videos in response to linguistic queries persists, largely due to the inefficiency in temporal grounding and limited pre-trained context…

Large language models (LLMs) demonstrate impressive performance but lack the flexibility to adapt to human preferences quickly without retraining. In this work, we introduce Test-time Preference Optimization (TPO), a framework that aligns…

Proximal Policy Optimization (PPO) is central to aligning Large Language Models (LLMs) in reasoning tasks with verifiable rewards. However, standard token-level PPO struggles in this setting due to the instability of temporal credit…

Video dubbing aims to translate original speech in visual media programs from the source language to the target language, relying on neural machine translation and text-to-speech technologies. Due to varying information densities across…

Temperature is a crucial hyperparameter in large language models (LLMs), controlling the trade-off between exploration and exploitation during text generation. High temperatures encourage diverse but noisy outputs, while low temperatures…

In an era where tool-augmented AI agents are becoming increasingly vital, our findings highlight the ability of Group Relative Policy Optimization (GRPO) to empower SLMs, which are traditionally constrained in tool use. The ability to use…

Applying Reinforcement Learning (RL) to Video Large Language Models (Video-LLMs) shows significant promise for complex video reasoning. However, popular Reinforcement Fine-Tuning (RFT) methods, such as outcome-based Group Relative Policy…

Despite advances in pretraining with extended context lengths, large language models (LLMs) still face challenges in effectively utilizing real-world long-context information, primarily due to insufficient long-context alignment caused by…

Multimodal Large Language Models (MLLMs) are powerful at integrating diverse data, but they often struggle with complex reasoning. While Reinforcement learning (RL) can boost reasoning in LLMs, applying it to MLLMs is tricky. Common issues…

Accurate analysis of industrial time-series big data is critical for the Prognostics and Health Management (PHM) of industrial equipment. While recent advancements in Large Language Models (LLMs) have shown promise in time-series analysis,…

Unified multimodal pretraining has emerged as a promising paradigm for jointly modeling language and vision within a single foundation model. However, existing approaches largely rely on implicit or indirect alignment signals and remain…

Recent advances in Large Language Models (LLMs) have led to significant breakthroughs in video understanding. However, existing models still struggle with long video processing due to the context length constraint of LLMs and the vast…

Self-supervised reinforcement learning (RL) presents a promising approach for enhancing the reasoning capabilities of Large Language Models (LLMs) without reliance on expensive human-annotated data. However, we find that existing methods…

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…

Aligning large-scale vision-language models (VLMs) for complex reasoning via reinforcement learning is often hampered by the limitations of existing policy optimization algorithms, such as static training schedules and the rigid, uniform…

Understanding long-form video content presents significant challenges due to its temporal complexity and the substantial computational resources required. In this work, we propose an agent-based approach to enhance both the efficiency and…

Token pruning has emerged as a mainstream approach for developing efficient Video Large Language Models (Video LLMs). This work revisits and advances the two predominant token-pruning paradigms: attention-based selection and…

Reinforcement learning with verifiable rewards (RLVR) has significantly advanced the reasoning ability of vision-language models (VLMs). However, the inherent text-dominated nature of VLMs often leads to insufficient visual faithfulness,…

Optimization problems often require domain-specific expertise to design problem-dependent methodologies. Recently, several approaches have gained attention by integrating large language models (LLMs) into genetic algorithms. Building on…

This paper presents VideoStreaming, an advanced vision-language large model (VLLM) for video understanding, that capably understands arbitrary-length video with a constant number of video tokens streamingly encoded and adaptively selected.…