Hsuan Su

jacksukk's activity

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

upvoted a paper 2 months ago

Chem-R: Learning to Reason as a Chemist

Paper • 2510.16880 • Published Oct 19 • 52

upvoted a collection 2 months ago

VisionLM

Collection

1867 items • Updated 5 days ago • 138

upvoted a paper 2 months ago

On Non-interactive Evaluation of Animal Communication Translators

Paper • 2510.15768 • Published Oct 17 • 2

upvoted 2 papers 3 months ago

Don't Waste Mistakes: Leveraging Negative RL-Groups via Confidence Reweighting

Paper • 2510.08696 • Published Oct 9 • 14

Webscale-RL: Automated Data Pipeline for Scaling RL Data to Pretraining Levels

Paper • 2510.06499 • Published Oct 7 • 31

upvoted a collection 3 months ago

Awesome papers from 臺大李宏毅 (Hung-yi Lee)

Collection

Recent papers authored by Hung-yi Lee. Sorted by ID • 8 items • Updated Oct 24 • 17

upvoted 14 papers 3 months ago

Pseudo2Real: Task Arithmetic for Pseudo-Label Correction in Automatic Speech Recognition

Paper • 2510.08047 • Published Oct 9 • 7

Agent Learning via Early Experience

Paper • 2510.08558 • Published Oct 9 • 269

IMPACT: Iterative Mask-based Parallel Decoding for Text-to-Audio Generation with Diffusion Modeling

Paper • 2506.00736 • Published May 31 • 10

Vibe Checker: Aligning Code Evaluation with Human Preference

Paper • 2510.07315 • Published Oct 8 • 32

Multi-Agent Tool-Integrated Policy Optimization

Paper • 2510.04678 • Published Oct 6 • 30

DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model with Self-Generated Cross-Modal Alignment

Paper • 2507.02768 • Published Jul 3 • 18

SHANKS: Simultaneous Hearing and Thinking for Spoken Language Models

Paper • 2510.06917 • Published Oct 8 • 34

Game-Time: Evaluating Temporal Dynamics in Spoken Language Models

Paper • 2509.26388 • Published Sep 30 • 26

Learning to Reason for Hallucination Span Detection

Paper • 2510.02173 • Published Oct 2 • 18

Knapsack RL: Unlocking Exploration of LLMs via Optimizing Budget Allocation

Paper • 2509.25849 • Published Sep 30 • 47

DeepSearch: Overcome the Bottleneck of Reinforcement Learning with Verifiable Rewards via Monte Carlo Tree Search

Paper • 2509.25454 • Published Sep 29 • 140

TruthRL: Incentivizing Truthful LLMs via Reinforcement Learning

Paper • 2509.25760 • Published Sep 30 • 55

HalluLens: LLM Hallucination Benchmark

Paper • 2504.17550 • Published Apr 24 • 2

Synthetic bootstrapped pretraining

Paper • 2509.15248 • Published Sep 17 • 8