Peking University

Activity Feed Request to join this org

authored 7 papers about 1 month ago

Human Decision-making is Susceptible to AI-driven Manipulation

Paper • 2502.07663 • Published Feb 11, 2025

SocialEval: Evaluating Social Intelligence of Large Language Models

Paper • 2506.00900 • Published Jun 1, 2025

JumpStarter: Human-AI Planning with Task-Structured Context Curation

Paper • 2410.03882 • Published Oct 4, 2024

Generalization or Memorization: Dynamic Decoding for Mode Steering

Paper • 2510.22099 • Published Oct 25, 2025 • 4

Cognition-of-Thought Elicits Social-Aligned Reasoning in Large Language Models

Paper • 2509.23441 • Published Sep 27, 2025

Simulating and Understanding Deceptive Behaviors in Long-Horizon Interactions

Paper • 2510.03999 • Published Oct 5, 2025

Deeper is Not Always Better: Mitigating the Alignment Tax via Confident Layer Decoding

Paper • 2606.21906 • Published Jun 20 • 26

submitted a paper to Daily Papers about 1 month ago

Deeper is Not Always Better: Mitigating the Alignment Tax via Confident Layer Decoding

Paper • 2606.21906 • Published Jun 20 • 26

authored a paper 5 months ago

daVinci-Env: Open SWE Environment Synthesis at Scale

Paper • 2603.13023 • Published Mar 13 • 30

authored a paper 6 months ago

daVinci-Dev: Agent-native Mid-training for Software Engineering

Paper • 2601.18418 • Published Jan 26 • 126

authored a paper 7 months ago

OpenDataArena: A Fair and Open Arena for Benchmarking Post-Training Dataset Value

Paper • 2512.14051 • Published Dec 16, 2025 • 47

authored 2 papers 10 months ago

Universal Image Restoration Pre-training via Degradation Classification

Paper • 2501.15510 • Published Jan 26, 2025 • 1

Universal Image Restoration Pre-training via Masked Degradation Classification

Paper • 2510.13282 • Published Oct 15, 2025 • 11

authored 2 papers about 1 year ago

Can One Domain Help Others? A Data-Centric Study on Multi-Domain Reasoning via Reinforcement Learning

Paper • 2507.17512 • Published Jul 23, 2025 • 37

InverTune: Removing Backdoors from Multimodal Contrastive Learning Models via Trigger Inversion and Activation Tuning

Paper • 2506.12411 • Published Jun 14, 2025

authored a paper about 1 year ago

MetaMind: Modeling Human Social Thoughts with Metacognitive Multi-Agent Systems

Paper • 2505.18943 • Published May 25, 2025 • 25

authored a paper over 1 year ago

Unveiling the Mist over 3D Vision-Language Understanding: Object-centric Evaluation with Chain-of-Analysis

Paper • 2503.22420 • Published Mar 28, 2025

authored a paper over 1 year ago

CipherBank: Exploring the Boundary of LLM Reasoning Capabilities through Cryptography Challenges

Paper • 2504.19093 • Published Apr 27, 2025 • 18

authored a paper over 1 year ago

TinyR1-32B-Preview: Boosting Accuracy with Branch-Merge Distillation

Paper • 2503.04872 • Published Mar 6, 2025 • 15

updated a model over 1 year ago

PekingU/rtdetr_v2_r101vd

Object Detection • 76.8M • Updated Feb 6, 2025 • 8.51k • 15