TIGER-Lab

university

https://wenhuchen.github.io/lab

Activity Feed Request to join this org

AI & ML interests

Natural Language Processing, Image Generation

Recent Activity

tonymwt authored a paper about 6 hours ago

Back to Basics: Revisiting ASR in the Age of Voice Agents

ZhuofengLi authored a paper about 6 hours ago

ImagenWorld: Stress-Testing Image Generation Models with Explainable Human Evaluation on Open-ended Real-World Tasks

eigentom authored a paper about 6 hours ago

Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction

View all activity

Papers

Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction

RationalRewards: Reasoning Rewards Scale Visual Generation Both Training and Test Time

View all Papers

authored a paper about 6 hours ago

Back to Basics: Revisiting ASR in the Age of Voice Agents

Paper • 2603.25727 • Published Mar 26 • 1

authored a paper about 6 hours ago

ImagenWorld: Stress-Testing Image Generation Models with Explainable Human Evaluation on Open-ended Real-World Tasks

Paper • 2603.27862 • Published Mar 29 • 31

authored a paper about 6 hours ago

Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction

Paper • 2605.05242 • Published 8 days ago • 78

authored a paper about 6 hours ago

Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction

Paper • 2605.05242 • Published 8 days ago • 78

authored a paper about 6 hours ago

Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction

Paper • 2605.05242 • Published 8 days ago • 78

in TIGER-Lab/MMEB-Leaderboard 2 days ago

Add Jina v5 omni MSR-VTT scores

#129 opened 3 days ago by

florian-hoenicke

submitted a paper to Daily Papers 2 days ago

Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction

Paper • 2605.05242 • Published 8 days ago • 78

authored a paper 3 days ago

Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL

Paper • 2604.28123 • Published 10 days ago • 44

in TIGER-Lab/MMEB-Leaderboard 5 days ago

Upload OmniMM-LI-3B-v0.json

#128 opened 5 days ago by

authored a paper 7 days ago

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation

Paper • 2604.24763 • Published 14 days ago • 69

authored a paper 7 days ago

Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling

Paper • 2604.28185 • Published 11 days ago • 87

in TIGER-Lab/MMLU-Pro 9 days ago

Set evaluation_framework to inspect-ai in eval.yaml

#44 opened 3 months ago by

updated a collection 12 days ago

VisPhyWorld

An execution-based framework that evaluates physical reasoning by generating executable simulator code from visual inputs. • 5 items • Updated 12 days ago

updated a dataset 12 days ago

TIGER-Lab/VisPhyWorld-Sub-All

Updated 12 days ago • 155

published a dataset 12 days ago

TIGER-Lab/VisPhyWorld-Sub-All

Updated 12 days ago • 155

authored 2 papers 13 days ago

AutoScape: Geometry-Consistent Long-Horizon Scene Generation

Paper • 2510.20726 • Published Oct 23, 2025

ReVSI: Rebuilding Visual Spatial Intelligence Evaluation for Accurate Assessment of VLM 3D Reasoning

Paper • 2604.24300 • Published 14 days ago • 65

in TIGER-Lab/MMEB-Leaderboard 14 days ago

Upload MMI-VL-Embedding.json

#127 opened 14 days ago by

updated a collection 19 days ago

VisPhyWorld

An execution-based framework that evaluates physical reasoning by generating executable simulator code from visual inputs. • 5 items • Updated 12 days ago

updated a Space 19 days ago

VisPhyWorld Comparator

Compare ground-truth and generated videos sample by sample