ResearchNovember 13, 2026
-40
🧊
V-JEPA-LM Crushes Open Video LLMs
A study examines whether refusal behavior can be uniformly removed across large language models such as Qwen, Gemma, Olmo, and Mistral using direction-based ablation.
#video models#V-JEPA#multimodal#benchmarks

🔥 What happened
Researchers at Hanyang University dropped V-JEPA-LM, a video-language model that reads dynamics directly from video instead of relying on static, text-aligned features. Their 4B model scores 72.1 across eleven video benchmarks, beating the best open 4B (61.1) and even the best open 8B (64.8).
💡 Why it matters
Standard VLMs answer speed questions at chance level, while a linear probe on frozen V-JEPA features hits 87%. Counterfactual supervision adds 4.5 points on average and a massive 38 points on speed questions—using just 4.53M samples and 32 tokens per frame, versus multi-stage pipelines with up to 256 tokens.
⚡ Our take
This is a wake-up call for anyone scaling video LLMs with more text and tokens. The encoder decides what's readable, not the data volume. Stick with SigLIP-style encoders and you'll keep missing the dynamics.
The title, summary and analysis of this item were produced automatically by an AI system and have not been editorially reviewed. They may contain errors, bias or omissions — when in doubt, read the linked original source.
Deep Dives & Similar Intelligence

Energy Model Shatters Sudoku Record
ResearchNovember 18, 2026

Liquid AI Topples GPT-6 on Decision Index
AI modelsNovember 16, 2026

Tencent's Hy4 Flash Slashes AI Costs
AI modelsNovember 16, 2026

Anthropic Strikes Back Before Its Mega-IPO
AI modelsNovember 14, 2026

Perplexity Smashes $1B Revenue Run Rate
Business & TrendsNovember 17, 2026