V-Rubrics and EgoTools accepted to EMNLP 2026: rubric-based RL and egocentric tool reasoning
liuziwei7 · x · 2026-10-26
shulintian announces two papers at EMNLP 2026 in Budapest (Oct 26, Hall H, HUNGEXPO): V-Rubrics uses rubric-based reinforcement learning (GRPO) to improve visual faithfulness of vision-language models, and EgoTools introduces a real-world egocentric video dataset and benchmark for reasoning about tool affordances, geometry, procedures, and causal effects.
More from Research
- Alibaba's four-generation TTS evolution: CosyVoice to Qwen-Audio-3.0-TTS — solyarisoftware · 2026-10-26
- LoopUno: 52-Minute LoRA Training Makes 3B LLM Draft 2 Tokens per Step Losslessly — LucaAmb · 2026-10-26
- Author publicly seeks emergency ICLR reviewers for three papers — _onionesque · 2026-10-26
- Cohere Labs' CulturalRiddles: top AI model hits 79%, some cultures just 22% — Cohere_Labs · 2026-10-26
- Cambridge NLIP brings 8 papers to EMNLP 2026, from tokenization to LLM agents — vlachos_nlp · 2026-10-26
- Context Bombs: deception tricks make attacking AI agents 23× costlier, zero success — tracebit · 2026-10-26