Tsinghua IIGroup

university

https://iigroup.github.io/

AI & ML interests

Fundamental Al Methods; Perception & World Modeling; Reasoning & Generation; Action & Interaction

Recent Activity

wanng authored a paper about 23 hours ago

UniEX: An Effective and Efficient Framework for Unified Information Extraction via a Span-extractive Perspective

wanng authored a paper about 2 months ago

E2A-Bench: Benchmarking Evidence-to-Action Reliability in Financial Chart Reasoning

wanng authored a paper about 2 months ago

CoWork-X: Experience-Optimized Co-Evolution for Multi-Agent Collaboration System

View all activity

Papers

Learning Where Outcomes Change:Credit-Addressable Reasoning for Multimodal Geometry

WebRISE: Requirement-Induced State Evaluation for MLLM-Generated Web Artifacts

View all Papers

authored a paper about 23 hours ago

UniEX: An Effective and Efficient Framework for Unified Information Extraction via a Span-extractive Perspective

Paper • 2305.10306 • Published May 22, 2023 • 1

authored 2 papers about 2 months ago

E2A-Bench: Benchmarking Evidence-to-Action Reliability in Financial Chart Reasoning

Paper • 2609.14302 • Published Sep 13 • 3

CoWork-X: Experience-Optimized Co-Evolution for Multi-Agent Collaboration System

Paper • 2602.05004 • Published Feb 4

submitted 2 papers to Daily Papers about 2 months ago

E2A-Bench: Benchmarking Evidence-to-Action Reliability in Financial Chart Reasoning

Paper • 2609.14302 • Published Sep 13 • 3

Learning Sparse Decision Trees via Transformer Variational Auto-Encoders

Paper • 2609.01430 • Published Sep 1 • 3

authored a paper 2 months ago

Learning Where Outcomes Change:Credit-Addressable Reasoning for Multimodal Geometry

Paper • 2608.30457 • Published Aug 31 • 5

submitted a paper to Daily Papers 2 months ago

Learning Where Outcomes Change:Credit-Addressable Reasoning for Multimodal Geometry

Paper • 2608.30457 • Published Aug 31 • 5

authored 3 papers 2 months ago

LongWoF-Bench: Evaluating EvoMap Genes for Verifiable Long-Workflow Tasks

Paper • 2608.23200 • Published Aug 24 • 8

AutoResearch: Insight In, Hallucination Out

Paper • 2608.17906 • Published Aug 23 • 25

Simple-OPD: Demystifying Warm-up for On-policy Distillation

Paper • 2608.06802 • Published Aug 7 • 1

submitted 2 papers to Daily Papers 2 months ago

LongWoF-Bench: Evaluating EvoMap Genes for Verifiable Long-Workflow Tasks

Paper • 2608.23200 • Published Aug 24 • 8

AutoResearch: Insight In, Hallucination Out

Paper • 2608.17906 • Published Aug 23 • 25

authored a paper 3 months ago

Route by Kinematics, Act by Observation: Kinematics-Supervised Expert Routing in MoE-Augmented VLA

Paper • 2607.26807 • Published Jul 29 • 1

authored 2 papers 5 months ago

WebRISE: Requirement-Induced State Evaluation for MLLM-Generated Web Artifacts

Paper • 2606.03220 • Published Jun 2 • 11

Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO

Paper • 2605.30789 • Published Jun 2 • 26

authored a paper 5 months ago

Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO

Paper • 2605.30789 • Published Jun 2 • 26

authored a paper 5 months ago

SIN-Bench: Tracing Native Evidence Chains in Long-Context Multimodal Scientific Interleaved Literature

Paper • 2601.10108 • Published Jan 15 • 7

authored a paper 5 months ago

Qwen-Image-Flash: Beyond Objective Design

Paper • 2606.03746 • Published Jun 2 • 38

submitted a paper to Daily Papers 5 months ago

WebRISE: Requirement-Induced State Evaluation for MLLM-Generated Web Artifacts

Paper • 2606.03220 • Published Jun 2 • 11

submitted a paper to Daily Papers 5 months ago

Qwen-Image-Flash: Beyond Objective Design

Paper • 2606.03746 • Published Jun 2 • 38