MassAlloc Attention: Let Attention Allocate Its Own Compute
Paper • 2609.32712 • Published • 6
GuoLiangTang
Tommy930
AI & ML interests
LLM，NLP，ML
Recent Activity
upvoted a paper about 1 hour ago
MassAlloc Attention: Let Attention Allocate Its Own Compute upvoted a paper about 1 hour ago
AdaTutoRank: Learning to Rerank Document Sets via Adaptive Tutoring Optimization for RAG and Deep Research upvoted a paper about 1 hour ago
Diffusion Reward ModelsOrganizations
None yet
upvoted 6
papers about 1 hour ago
AdaTutoRank: Learning to Rerank Document Sets via Adaptive Tutoring Optimization for RAG and Deep Research
Paper • 2609.32472 • Published • 16
Diffusion Reward Models
Paper • 2609.33803 • Published • 16
Self-Evolving Coding Agents: From Digital Programs to Physical-World Intelligence
Paper • 2609.35432 • Published • 40
SLCA-GRPO: Resolving Cross-Segment Credit Misattribution in Tool-Calling RL
Paper • 2609.29050 • Published • 8
RayOrch: Programming and Executing Lineage-Controlled Multi-Grain Dataflows for Foundation-Model Data Preparation
Paper • 2609.18703 • Published • 47
upvoted 7
papers about 20 hours ago
Decision Hijacking: Prompt Injection Attacks on Jev's Typed Probabilistic Decisions
Paper • 2609.28613 • Published • 1
REFLEX with Jev for Efficient Selective Control in LLM Agents
Paper • 2609.26532 • Published • 1
Visual Jev: Accurate and Efficient Decisions from Shared Visual Context
Paper • 2609.25845 • Published • 2
Jev in the Wild: A Data-Driven Analysis of the Jev Model's Functionality, Applications and Ecosystem
Paper • 2609.30216 • Published • 9
Just Ask Jev: Reinforcement Learning for Calibrated Decisions as a Zero-Shot Detector of AI Alignment Failures
Paper • 2609.29429 • Published • 14
JEV-Star: Fast, Low-Cost StarCraft II Control with Language-Model Planning
Paper • 2609.27331 • Published • 5
Jev-Mem: System-One-Controlled Agentic Memory for Efficient AI Agents
Paper • 2609.23986 • Published • 28
upvoted 5
papers 4 days ago
DeltaWAM: Delta World Action Models for Bimanual Manipulation
Paper • 2609.28811 • Published • 8
WanPE: Towards Cinematic Prompt Enhancement for Modern Text-to-Video Generation
Paper • 2609.30221 • Published • 39
World Action Agent: Harnessing VLMs for Robot Manipulation via World Action Rehearsal
Paper • 2609.29964 • Published • 9
Qwen-Planner-Agent: A Closed-Loop AI-for-AI Framework for Real-World Mobile Planner Agents
Paper • 2609.29892 • Published • 19
Verifiable Hidden Dynamics Play: Generating Agentic RL Environments from Solved Mechanisms
Paper • 2609.27321 • Published • 21
upvoted 2
papers 5 days ago