Shaobai Jiang

shaobaij's activity

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

upvoted a paper about 15 hours ago

R-KV: Redundancy-aware KV Cache Compression for Reasoning Models

Paper • 2505.24133 • Published May 30, 2025 • 2

upvoted 10 papers about 19 hours ago

Causal Judge Evaluation: Calibrated Surrogate Metrics for LLM Systems

Paper • 2512.11150 • Published 25 days ago • 5

Beyond Real: Imaginary Extension of Rotary Position Embeddings for Long-Context LLMs

Paper • 2512.07525 • Published 28 days ago • 57

MOA: Multi-Objective Alignment for Role-Playing Agents

Paper • 2512.09756 • Published 26 days ago • 4

Scaling Behavior of Discrete Diffusion Language Models

Paper • 2512.10858 • Published 25 days ago • 7

TreeGRPO: Tree-Advantage GRPO for Online RL Post-Training of Diffusion Models

Paper • 2512.08153 • Published 28 days ago • 7

From Next-Token to Next-Block: A Principled Adaptation Path for Diffusion LLMs

Paper • 2512.06776 • Published 29 days ago • 25

DoVer: Intervention-Driven Auto Debugging for LLM Multi-Agent Systems

Paper • 2512.06749 • Published 29 days ago • 27

Long-horizon Reasoning Agent for Olympiad-Level Mathematical Problem Solving

Paper • 2512.10739 • Published 25 days ago • 46

Native Parallel Reasoner: Reasoning in Parallelism via Self-Distilled Reinforcement Learning

Paper • 2512.07461 • Published 28 days ago • 75

OPV: Outcome-based Process Verifier for Efficient Long Chain-of-Thought Verification

Paper • 2512.10756 • Published 25 days ago • 34

upvoted 3 papers about 21 hours ago

Evaluating Gemini Robotics Policies in a Veo World Simulator

Paper • 2512.10675 • Published 25 days ago • 17

The Universal Weight Subspace Hypothesis

Paper • 2512.05117 • Published Dec 4, 2025 • 2

Weird Generalization and Inductive Backdoors: New Ways to Corrupt LLMs

Paper • 2512.09742 • Published 26 days ago • 3

upvoted 2 papers 2 days ago

KVzip: Query-Agnostic KV Cache Compression with Context Reconstruction

Paper • 2505.23416 • Published May 29, 2025 • 12

AttentionPredictor: Temporal Pattern Matters for Efficient LLM Inference

Paper • 2502.04077 • Published Feb 6, 2025 • 1

upvoted 4 papers 3 days ago

GR-Dexter Technical Report

Paper • 2512.24210 • Published 6 days ago • 20

mHC: Manifold-Constrained Hyper-Connections

Paper • 2512.24880 • Published 5 days ago • 199

PaperDebugger: A Plugin-Based Multi-Agent System for In-Editor Academic Writing, Review, and Editing

Paper • 2512.02589 • Published Dec 2, 2025 • 68

CUDA-L2: Surpassing cuBLAS Performance for Matrix Multiplication through Reinforcement Learning

Paper • 2512.02551 • Published Dec 2, 2025 • 12