TRACE: Rollout-Guided Quantization-Aware Training for FP4 Reinforcement Learning of MoE Language Models
Paper • 2610.07767 • Published • 59
Daniel Wang
tuidan
AI & ML interests
Efficient AI / LLM / ML System
Recent Activity
upvoted a paper about 5 hours ago
TRACE: Rollout-Guided Quantization-Aware Training for FP4 Reinforcement Learning of MoE Language Models authored a paper about 9 hours ago
SVD-LLM V2: Optimizing Singular Value Truncation for Large Language Model Compression authored a paper about 9 hours ago
QUADS: Stabilizing NVFP4 Reinforcement Learning for MoE via QUantization-error Alignment across Dual SidesOrganizations
upvoted a paper about 5 hours ago
authored 4
papers about 9 hours ago
SVD-LLM V2: Optimizing Singular Value Truncation for Large Language Model Compression
Paper • 2503.12340 • Published
QUADS: Stabilizing NVFP4 Reinforcement Learning for MoE via QUantization-error Alignment across Dual Sides
Paper • 2607.15810 • Published • 1
TRACE: Rollout-Guided Quantization-Aware Training for FP4 Reinforcement Learning of MoE Language Models
Paper • 2610.07767 • Published • 59
AgentSpec: Speculative Decoding for Batch Inference of LLM Agents
Paper • 2608.24004 • Published
submitted a
paper to Daily Papers about 13 hours ago
authored 5
papers about 2 years ago
Efficient Large Language Models: A Survey
Paper • 2312.03863 • Published • 4
SVD-LLM: Truncation-aware Singular Value Decomposition for Large Language Model Compression
Paper • 2403.07378 • Published • 4
Electrocardiogram Instruction Tuning for Report Generation
Paper • 2403.04945 • Published • 2
The Internet of Things in the Era of Generative AI: Vision and Challenges
Paper • 2401.01923 • Published • 1
D2O: Dynamic Discriminative Operations for Efficient Generative Inference of Large Language Models
Paper • 2406.13035 • Published • 3