arXiv Computer Vision
Ask About the Right Moment: Training-Free Object Identity Reasoning for Video-Language Models
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Computer Vision
1d ago
What Do Verifiable Rewards Teach Video-Language Models About Time? A Controlled Multi-Model Study
arXiv:2610.03792v2 Announce Type: replace Abstract: Reinforcement learning from verifiable rewards (RLVR) has produced large reasoning gains in language models, and verifiable video benchmarks make i...
arXiv AI
Jun 4
From Segments to Scenes: Temporal Understanding for Agentic Autonomous Driving via Vision-Language Models
arXiv:2512. 05277v4 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) are increasingly deployed as the perception and reasoning backbone of autonomous agents acting in the wild, with autonomous driving (AD) being one of the most safety-critical instances.
arXiv AI
Jun 2
From Segments to Scenes: Temporal Understanding in Autonomous Driving via Vision-Language Model
arXiv:2512. 05277v3 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) are increasingly deployed as the perception and reasoning backbone of autonomous agents acting in the wild, with autonomous driving (AD) being one of the most safety-critical instances.
arXiv Computation and Language
Sep 10
VLX-VR: An Agentic-Aware Video Reasoning Model
arXiv:2609.09985v1 Announce Type: new Abstract: Real-world video understanding requires integrating visual, audio, textual, and temporal evidence distributed across a video. Yet many pipelines use a...
arXiv AI
Oct 9
VAMR: Multi-Question Agentic Reasoning for Efficient Long-Form Video Understanding
VAMR is a video agent that handles multiple questions about a single long‑form video using a single shared tool‑use trajectory, rather than treating each question separately. It employs question‑conditioned visual perception, layered multi‑question memory, and a question‑horizon policy optimization to jointly acquire evidence and progressively build a shared understanding. In benchmark tests (LVBench, Video‑Holmes, LongVideoBench), VAMR outperforms prior methods, achieving higher accuracy and fewer reasoning rounds and processed frames.
arXiv Computer Vision
Oct 5
Behavior Pack Optimization for Video MLLM Post-Training
The paper introduces Behavior Pack Optimization (BPO), a post‑training method for video multimodal large language models that replaces single‑response rewards with a set of outputs across counterfactual views. BPO enforces stability when interventions are irrelevant, sensitivity when key evidence is removed, and abstention when no evidence remains, using an anchor‑relative advantage to keep the objective stable with small pack sizes. Experiments on datasets such as TempCompass, MVBench, and NExT‑QA show that BPO improves macro accuracy and abstention metrics for models like Qwen2.5‑VL‑7B‑Instruct, with gains that transfer to other benchmarks and models.