Yanqi Dai

YanqiDai's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 1 day ago

Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation

Paper • 2602.12125 • Published 2 days ago • 55

upvoted a paper 9 days ago

FASA: Frequency-aware Sparse Attention

Paper • 2602.03152 • Published 11 days ago • 146

upvoted 2 papers 10 days ago

SWE-Master: Unleashing the Potential of Software Engineering Agents via Post-Training

Paper • 2602.03411 • Published 11 days ago • 36

SWE-World: Building Software Engineering Agents in Docker-Free Environments

Paper • 2602.03419 • Published 11 days ago • 39

upvoted a paper 13 days ago

Improvable Gap Balancing for Multi-Task Learning

Paper • 2307.15429 • Published Jul 28, 2023 • 2

upvoted a paper 15 days ago

CharacterBox: Evaluating the Role-Playing Capabilities of LLMs in Text-Based Virtual Worlds

Paper • 2412.05631 • Published Dec 7, 2024 • 2

upvoted 2 collections 15 days ago

MMRole

Collection

Accepted for ICLR 2025 • 4 items • Updated 12 days ago • 1

MathForge

Collection

Accepted for ICLR 2026 • 4 items • Updated 12 days ago • 1

upvoted a paper 15 days ago

Everything in Its Place: Benchmarking Spatial Intelligence of Text-to-Image Models

Paper • 2601.20354 • Published 17 days ago • 110

upvoted a paper 17 days ago

Harder Is Better: Boosting Mathematical Reasoning via Difficulty-Aware GRPO and Multi-Aspect Question Reformulation

Paper • 2601.20614 • Published 17 days ago • 118

upvoted a paper 22 days ago

Adaptive Task Balancing for Visual Instruction Tuning via Inter-Task Contribution and Intra-Task Difficulty

Paper • 2403.04343 • Published Mar 7, 2024 • 1

upvoted a paper 2 months ago

Mixture of Horizons in Action Chunking

Paper • 2511.19433 • Published Nov 24, 2025 • 18

upvoted a paper 4 months ago

LaSeR: Reinforcement Learning with Last-Token Self-Rewarding

Paper • 2510.14943 • Published Oct 16, 2025 • 40

upvoted a collection 5 months ago

LLaDA

Collection

3 items • Updated 1 day ago • 10

upvoted 2 papers 6 months ago

Omni-Effects: Unified and Spatially-Controllable Visual Effects Generation

Paper • 2508.07981 • Published Aug 11, 2025 • 63

ReasonRank: Empowering Passage Ranking with Strong Reasoning Ability

Paper • 2508.07050 • Published Aug 9, 2025 • 117

upvoted a paper 8 months ago

MMRole: A Comprehensive Framework for Developing and Evaluating Multimodal Role-Playing Agents

Paper • 2408.04203 • Published Aug 8, 2024 • 2

upvoted 2 papers 9 months ago

LLaDA-V: Large Language Diffusion Models with Visual Instruction Tuning

Paper • 2505.16933 • Published May 22, 2025 • 34

UniVG-R1: Reasoning Guided Universal Visual Grounding with Reinforcement Learning

Paper • 2505.14231 • Published May 20, 2025 • 53