AsyncOPD: How Stale Can On-Policy Distillation Be?
Paper • 2606.24143 • Published • 31
AI & ML interests
None defined yet.
Recent Activity
View all activity
Team members 50 private
JakeOh
authored 4
papers 5 days ago
EfficientRollout: System-Aware Self-Speculative Decoding for RL Rollouts
Paper • 2606.18967 • Published • 24
ParallelBench: Understanding the Trade-offs of Parallel Decoding in Diffusion LLMs
Paper • 2510.04767 • Published • 28
Optimized Feature Generation for Tabular Data via LLMs with Decision Tree Reasoning
Paper • 2406.08527 • Published • 1
wjkang
submitted a
paper to Daily Papers about 1 month ago
FuriosaMJLEE
submitted a
paper to Daily Papers about 2 months ago
FuriosaMJLEE
authored 5
papers 12 months ago
State-offset Tuning: State-based Parameter-Efficient Fine-Tuning for State Space Models
Paper • 2503.03499 • Published • 5
VersaPRM: Multi-Domain Process Reward Model via Synthetic Reasoning Data
Paper • 2502.06737 • Published
Draft-based Approximate Inference for LLMs
Paper • 2506.08373 • Published • 4
UNCAGE: Contrastive Attention Guidance for Masked Generative Transformers in Text-to-Image Generation
Paper • 2508.05399 • Published • 17
XQuant: Breaking the Memory Wall for LLM Inference with KV Cache Rematerialization
Paper • 2508.10395 • Published • 42
wjkang
authored 2
papers 12 months ago
JakeOh
authored 3
papers 12 months ago
Sparsified State-Space Models are Efficient Highway Networks
Paper • 2505.20698 • Published • 2
Hierarchical Context Merging: Better Long Context Understanding for Pre-trained LLMs
Paper • 2404.10308 • Published
UNCAGE: Contrastive Attention Guidance for Masked Generative Transformers in Text-to-Image Generation
Paper • 2508.05399 • Published • 17
wjkang
authored 2
papers about 1 year ago
JakeOh
authored a
paper about 1 year ago
wjkang
authored a
paper about 1 year ago