Shaobai Jiang

shaobaij's activity

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

upvoted a paper about 19 hours ago

Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators

Paper • 2602.22647 • Published 5 days ago • 2

upvoted 2 papers 1 day ago

General Agent Evaluation

Paper • 2602.22953 • Published 5 days ago • 11

AgentDropoutV2: Optimizing Information Flow in Multi-Agent Systems via Test-Time Rectify-or-Reject Pruning

Paper • 2602.23258 • Published 4 days ago • 27

upvoted 17 papers 2 days ago

Post-LayerNorm Is Back: Stable, ExpressivE, and Deep

Paper • 2601.19895 • Published Jan 27 • 24

Fast KVzip: Efficient and Accurate LLM Inference with Gated KV Eviction

Paper • 2601.17668 • Published Jan 25 • 7

Towards Automated Kernel Generation in the Era of LLMs

Paper • 2601.15727 • Published Jan 22 • 19

The Responsibility Vacuum: Organizational Failure in Scaled Agent Systems

Paper • 2601.15059 • Published Jan 21 • 4

A BERTology View of LLM Orchestrations: Token- and Layer-Selective Probes for Efficient Single-Pass Classification

Paper • 2601.13288 • Published Jan 19 • 14

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models

Paper • 2601.14004 • Published Jan 20 • 47

Lost in the Prompt Order: Revealing the Limitations of Causal Attention in Language Models

Paper • 2601.14152 • Published Jan 20 • 6

Privacy Collapse: Benign Fine-Tuning Can Break Contextual Privacy in Language Models

Paper • 2601.15220 • Published Jan 21 • 9

Entropy Sentinel: Continuous LLM Accuracy Monitoring from Decoding Entropy Traces in STEM

Paper • 2601.09001 • Published Jan 13 • 18

Agentic Uncertainty Quantification

Paper • 2601.15703 • Published Jan 22 • 9

Agentic Confidence Calibration

Paper • 2601.15778 • Published Jan 22 • 6

Paper2Rebuttal: A Multi-Agent Framework for Transparent Author Response Assistance

Paper • 2601.14171 • Published Jan 20 • 51

GameTalk: Training LLMs for Strategic Conversation

Paper • 2601.16276 • Published Jan 22 • 13

Dancing in Chains: Strategic Persuasion in Academic Rebuttal via Theory of Mind

Paper • 2601.15715 • Published Jan 22 • 14

Elastic Attention: Test-time Adaptive Sparsity Ratios for Efficient Transformers

Paper • 2601.17367 • Published Jan 24 • 34

Behavior Knowledge Merge in Reinforced Agentic Models

Paper • 2601.13572 • Published Jan 20 • 25

Jet-RL: Enabling On-Policy FP8 Reinforcement Learning with Unified Training and Rollout Precision Flow

Paper • 2601.14243 • Published Jan 20 • 23