Yogesh Kulkarni

Yogesh Kulkarni, Pooyan Fazli

Recent advances in video-large language models (Video-LLMs) have led to significant progress in video understanding. Current preference optimization methods often rely on proprietary APIs or human-annotated captions to generate preference data (i.e., pairs of model outputs ranked by quality or alignment with human judgment), which is then used to train models for video-language alignment. This approach is both costly and labor-intensive. To address this limitation, we introduce VideoSAVi (Self-Aligned Video Language Model), a self-training pipeline that enables Video-LLMs to learn from video content without external supervision. Our approach includes a self-critiquing mechanism that identifies reasoning errors in the model's initial responses and generates improved alternatives, creating preference pairs directly from video content. VideoSAVi then applies Direct Preference Optimization (DPO) to iteratively train the model using the preference data, thus enhancing its temporal and spatial reasoning for video understanding. Experiments show that VideoSAVi delivers significant improvements across multiple benchmarks, including a +4.2 percentage point gain on MVBench, +3.9 on PerceptionTest, and +6.8 on the challenging EgoSchema dataset compared to baseline models. Our model-agnostic approach is computationally efficient, requiring only 32 frames, offering a promising direction for self-aligned video understanding without reliance on external models or annotations.

Yogesh Kulkarni, Pooyan Fazli

Multimodal reasoning over long-horizon video is challenging due to the need for precise spatiotemporal fusion and alignment across modalities. While recent methods such as Group Relative Policy Optimization (GRPO) have shown promise in this domain, they suffer from three key limitations: (1) data inefficiency from their on-policy design, (2) a vanishing advantage problem, where identical or near-identical rewards within a group eliminate the learning signal by producing zero-valued advantages, and (3) uniform credit assignment that fails to emphasize critical reasoning steps. We introduce AVATAR (Audio-Video Agent for Alignment and Reasoning), a framework that addresses these limitations through two core components: (1) an off-policy training architecture that improves sample efficiency and resolves vanishing advantages by reusing past experiences with greater reward diversity, and (2) Temporal Advantage Shaping (TAS), a novel credit assignment strategy that upweights key reasoning phases during learning. AVATAR achieves strong performance across various benchmarks, outperforming the Qwen2.5-Omni baseline by +5.4on MMVU, +4.9 on OmniBench, and +4.5 on Video-Holmes, while demonstrating over 35% higher sample efficiency.

Chaoyu Li, Yogesh Kulkarni, Pooyan Fazli

The computational cost of training multimodal large language models (MLLMs) rapidly increases with the number of tokens involved. Existing efficiency methods primarily target inference and rely on token reduction or merging, offering limited benefit during training. In this paper, we propose ReGATE (Reference$-$Guided Adaptive Token Elision), an adaptive token pruning method for accelerating MLLM training. Specifically, ReGATE adopts a teacher-student framework in which the MLLM being trained serves as the student, and a frozen reference large language model (LLM) acts as the teacher. The teacher computes per-token reference losses, which are combined with an exponential moving average (EMA) of the student's own difficulty scores. This adaptive difficulty-based scoring enables the selective processing of crucial tokens while bypassing less informative ones in the forward pass, significantly reducing computational overhead. Experiments demonstrate that ReGATE, when applied to VideoLLaMA2, matches the peak accuracy of standard training on MVBench up to 2$\times$ faster, using only 35% of the tokens. With additional training, it even surpasses the baseline on several multimodal benchmarks, all while reducing the total token count by over 41%. Code and models will be released soon.