Peking University

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

xianbao submitted a paper 3 days ago

The Curse and Blessing of Mean Bias in FP4-Quantized LLM Training

jcy submitted a paper 17 days ago

From Blind Spots to Gains: Diagnostic-Driven Iterative Training for Large Multimodal Models

thkelper authored a paper about 1 month ago

SSL: Sweet Spot Learning for Differentiated Guidance in Agentic Optimization

View all activity

Papers

Diff4Splat: Controllable 4D Scene Generation with Latent Dynamic Reconstruction Models

Detecting Data Contamination from Reinforcement Learning Post-training for Large Language Models

View all Papers

submitted a paper to Daily Papers 3 days ago

The Curse and Blessing of Mean Bias in FP4-Quantized LLM Training

Paper • 2603.10444 • Published 5 days ago • 7

authored a paper 4 months ago

RoboChallenge: Large-scale Real-robot Evaluation of Embodied Policies

Paper • 2510.17950 • Published Oct 20, 2025 • 9

authored 2 papers 5 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 a paper 5 months ago

Beyond Chemical QA: Evaluating LLM's Chemical Reasoning with Modular Chemical Operations

Paper • 2505.21318 • Published May 27, 2025 • 1

authored a paper 5 months ago

UniLiP: Adapting CLIP for Unified Multimodal Understanding, Generation and Editing

Paper • 2507.23278 • Published Jul 31, 2025 • 1

authored 5 papers 6 months ago

An Effective Meaningful Way to Evaluate Survival Models

Paper • 2306.01196 • Published Jun 1, 2023

LLaVA-o1: Let Vision Language Models Reason Step-by-Step

Paper • 2411.10440 • Published Nov 15, 2024 • 129

Stacking Brick by Brick: Aligned Feature Isolation for Incremental Face Forgery Detection

Paper • 2411.11396 • Published Nov 18, 2024

Guard Me If You Know Me: Protecting Specific Face-Identity from Deepfakes

Paper • 2505.19582 • Published May 26, 2025

Can Understanding and Generation Truly Benefit Together -- or Just Coexist?

Paper • 2509.09666 • Published Sep 11, 2025 • 34

authored a paper 10 months ago

Master: Meta Style Transformer for Controllable Zero-Shot and Few-Shot Artistic Style Transfer

Paper • 2304.11818 • Published Apr 24, 2023

authored a paper about 1 year ago

UFO: A Unified Approach to Fine-grained Visual Perception via Open-ended Language Interface

Paper • 2503.01342 • Published Mar 3, 2025 • 8

authored 2 papers about 1 year ago

S$^3$c-Math: Spontaneous Step-level Self-correction Makes Large Language Models Better Mathematical Reasoners

Paper • 2409.01524 • Published Sep 3, 2024 • 1

LogicPro: Improving Complex Logical Reasoning via Program-Guided Learning

Paper • 2409.12929 • Published Sep 19, 2024 • 2

updated 4 models about 1 year ago

PekingU/rtdetr_v2_r101vd

Object Detection • 76.8M • Updated Feb 6, 2025 • 3.41k • 13

PekingU/rtdetr_v2_r50vd

Object Detection • 43M • Updated Feb 6, 2025 • 25.7k • 28

PekingU/rtdetr_v2_r34vd

Object Detection • 31.5M • Updated Feb 6, 2025 • 659 • 7

PekingU/rtdetr_v2_r18vd

Object Detection • 20.2M • Updated Feb 6, 2025 • 95.3k • 5

in PekingU/rtdetr_v2_r18vd about 1 year ago

Update README.md

#1 opened about 1 year ago by