arXiv (All)
open access
Behavior Pack Optimization for Video MLLM Post-Training
Video multimodal large language models (MLLMs) keep climbing video question answering benchmarks, yet shuffling the frames, masking the segment that supports the answer, or occluding the target object barely changes their predictions. The accuracy rests on appearance and language priors, not on the
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- ActionCodec: What Makes for Good Action Tokenizers#1249352
- Validating, Not Sampling: Region-Level Robustness of Vision-Language and Vision-Language-Action Models#1036976
- SimpleMemVLA: A Simple but Effective Native-Video Memory for Vision-Language-Action Models#972594
- Watch, Remember, Reason: Human-View Video Understanding with MLLMs#266210
- Fast-VLA: You Only Think Once for Robot Manipulation#1356725
Record · ID 1187819
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive