Kuo-Hsin Tu

dapumptu's activity

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

upvoted 2 papers about 3 hours ago

FRMT: A Benchmark for Few-Shot Region-Aware Machine Translation

Paper • 2210.00193 • Published Oct 1, 2022 • 1

DiscoX: Benchmarking Discourse-Level Translation task in Expert Domains

Paper • 2511.10984 • Published Nov 14, 2025 • 6

upvoted 16 papers 1 day ago

Decouple Searching from Training: Scaling Data Mixing via Model Merging for Large Language Model Pre-training

Paper • 2602.00747 • Published 12 days ago • 9

Privasis: Synthesizing the Largest "Public" Private Dataset from Scratch

Paper • 2602.03183 • Published 9 days ago • 9

Learning Query-Specific Rubrics from Human Preferences for DeepResearch Report Generation

Paper • 2602.03619 • Published 9 days ago • 25

AgentArk: Distilling Multi-Agent Intelligence into a Single LLM Agent

Paper • 2602.03955 • Published 9 days ago • 8

From Data to Behavior: Predicting Unintended Model Behaviors Before Training

Paper • 2602.04735 • Published 8 days ago • 15

Learning Rate Matters: Vanilla LoRA May Suffice for LLM Fine-tuning

Paper • 2602.04998 • Published 8 days ago • 6

Late-to-Early Training: LET LLMs Learn Earlier, So Faster and Better

Paper • 2602.05393 • Published 7 days ago • 7

Exploring Knowledge Purification in Multi-Teacher Knowledge Distillation for LLMs

Paper • 2602.01064 • Published 11 days ago • 2

SEMA: Simple yet Effective Learning for Multi-Turn Jailbreak Attacks

Paper • 2602.06854 • Published 6 days ago • 6

Large Language Model Reasoning Failures

Paper • 2602.06176 • Published 7 days ago • 11

CodeCircuit: Toward Inferring LLM-Generated Code Correctness via Attribution Graphs

Paper • 2602.07080 • Published 6 days ago • 6

Reliable and Responsible Foundation Models: A Comprehensive Survey

Paper • 2602.08145 • Published 8 days ago • 8

QuantaAlpha: An Evolutionary Framework for LLM-Driven Alpha Mining

Paper • 2602.07085 • Published 6 days ago • 177

Steer2Adapt: Dynamically Composing Steering Vectors Elicits Efficient Adaptation of LLMs

Paper • 2602.07276 • Published 6 days ago • 10

TodoEvolve: Learning to Architect Agent Planning Systems

Paper • 2602.07839 • Published 4 days ago • 5

OPUS: Towards Efficient and Principled Data Selection in Large Language Model Pre-training in Every Iteration

Paper • 2602.05400 • Published 7 days ago • 291

upvoted 2 collections 5 days ago

Evaluation Suite for Hallucination of Multilingual LLMs

Collection

Datasets for the paper "Analyzing LLMs' Knowledge Boundary Cognition Across Languages Through the Lens of Internal Representations" • 4 items • Updated Jun 6, 2025 • 4

Typhoon 2.5

Collection

Typhoon 2.5 Text ThaiLLM release by SCB 10X. • 4 items • Updated 15 days ago • 1