Haoran Song

charles-martin4's activity

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

upvoted a paper 2 days ago

DreamForge-World 0.1 Preview: A Low-Compute Real-Time Controllable World Model

Paper • 2606.30292 • Published 7 days ago • 14

upvoted a paper 15 days ago

Configurable Clinical Information Extraction with Agentic RAG: What Works, What Breaks, and Why

Paper • 2606.19602 • Published 19 days ago • 4

upvoted 2 papers about 1 month ago

Forecasting Downstream Performance of LLMs With Proxy Metrics

Paper • 2605.18607 • Published May 18 • 14

MINTEval: Evaluating Memory under Multi-Target Interference in Long-Horizon Agent Systems

Paper • 2605.18565 • Published May 19 • 5

upvoted 5 papers about 2 months ago

Sparse Autoencoders enable Robust and Interpretable Fine-tuning of CLIP models

Paper • 2605.15961 • Published May 15 • 10

Multi-Objective and Mixed-Reward Reinforcement Learning via Reward-Decorrelated Policy Optimization

Paper • 2605.13641 • Published May 13 • 51

Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information

Paper • 2605.11609 • Published May 12 • 196

Q-RAG: Long Context Multi-step Retrieval via Value-based Embedder Training

Paper • 2511.07328 • Published May 4 • 16

EDU-CIRCUIT-HW: Evaluating Multimodal Large Language Models on Real-World University-Level STEM Student Handwritten Solutions

Paper • 2602.00095 • Published Apr 30 • 3

upvoted 2 papers 2 months ago

Significance and Stability Analysis of Gene-Environment Interaction using RGxEStat

Paper • 2604.03337 • Published Apr 3 • 1

LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model

Paper • 2604.20796 • Published Apr 22 • 244

upvoted 5 papers 3 months ago

Adam's Law: Textual Frequency Law on Large Language Models

Paper • 2604.02176 • Published Apr 2 • 509

Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability

Paper • 2604.06628 • Published Apr 8 • 329

ACES: Who Tests the Tests? Leave-One-Out AUC Consistency for Code Generation

Paper • 2604.03922 • Published Apr 5 • 53

GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning

Paper • 2604.02721 • Published Apr 3 • 638

GEMS: Agent-Native Multimodal Generation with Memory and Skills

Paper • 2603.28088 • Published Mar 30 • 87

upvoted 2 papers 4 months ago

HSImul3R: Physics-in-the-Loop Reconstruction of Simulation-Ready Human-Scene Interactions

Paper • 2603.15612 • Published Mar 16 • 153

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

Paper • 2602.22859 • Published Feb 26 • 150