OLAResearchX/LTB-AI
Viewer • Updated • 497 • 29
AI & ML interests
Large Language Models, Multimodal Learning, AI for Health
Recent Activity
View all activity
Papers
Label-free steering: Compressing test-time reinforcement learning into bias-only subspaces
MemoryAthena: Adaptive Routing over Latent and Generated Memories
jisxÂ
updated a
dataset 3 days ago
jisxÂ
published a
dataset 3 days ago
jisxÂ
authored 15
papers 3 days ago
Roleplaying with Structure: Synthetic Therapist-Client Conversation Generation from Questionnaires
Paper • 2510.25384 • Published
You Never Know a Person, You Only Know Their Defenses: Detecting Levels of Psychological Defense Mechanisms in Supportive Conversations
Paper • 2512.15601 • Published
A Parallel Cross-Lingual Benchmark for Multimodal Idiomaticity Understanding
Paper • 2601.08645 • Published
Test-Time Scaling of Reasoning Models for Machine Translation
Paper • 2510.06471 • Published • 2
XCR-Bench: A Multi-Task Benchmark for Evaluating Cultural Reasoning in LLMs
Paper • 2601.14063 • Published
Model-Based Quality Assessment for Massively Multilingual Parallel Data
Paper • 2606.00285 • Published • 1
Reasoning over Grammar: Can Synthetic Linguistic Reasoning Traces Enhance Low-Resource Machine Translation?
Paper • 2606.03782 • Published
CulturALL: Benchmarking Multilingual and Multicultural Competence of LLMs on Grounded Tasks
Paper • 2604.19262 • Published
Cross-Model Memory Transfer via Target-Side Reader Adaptation
Paper • 2608.17050 • Published • 8
Last Translation Benchmark
Paper • 2609.04173 • Published • 45
A Comparison of Language Modeling and Translation as Multilingual Pretraining Objectives
Paper • 2407.15489 • Published
SemEval-2025 Task 3: Mu-SHROOM, the Multilingual Shared Task on Hallucinations and Related Observable Overgeneration Mistakes
Paper • 2504.11975 • Published
Training Specialist Models without Reasoning Trajectories for Domain Expert Distillation
Paper • 2609.13770 • Published • 9
MemoryAthena: Adaptive Routing over Latent and Generated Memories
Paper • 2609.25853 • Published • 15
Label-free steering: Compressing test-time reinforcement learning into bias-only subspaces
Paper • 2609.18587 • Published • 3
jisxÂ
updated a
collection 3 days ago
jisxÂ
submitted a
paper to Daily Papers 3 days ago
naveenVakadaÂ
updated a
collection 7 days ago