Victor Jotham Ashioya
ashioyajotham
·
AI & ML interests
Hallucination in LLMs, AI Safety: alignment, red-teaming
Recent Activity
updated a dataset about 7 hours ago
ashioyajotham/CoT_Faithfulness_Dataset liked a model about 23 hours ago
zai-org/GLM-5.2 liked a model 3 months ago
google/gemma-4-E4B-itOrganizations
None yet
LLM Reasoning
-
Teaching Large Language Models to Reason with Reinforcement Learning
Paper • 2403.04642 • Published • 48 -
How Far Are We from Intelligent Visual Deductive Reasoning?
Paper • 2403.04732 • Published • 21 -
Common 7B Language Models Already Possess Strong Math Capabilities
Paper • 2403.04706 • Published • 18 -
DeepSeek-Prover: Advancing Theorem Proving in LLMs through Large-Scale Synthetic Data
Paper • 2405.14333 • Published • 47
finetuning
VLMs
Fav papers
-
Large-Scale Automatic Audiobook Creation
Paper • 2309.03926 • Published • 55 -
Agents: An Open-source Framework for Autonomous Language Agents
Paper • 2309.07870 • Published • 43 -
PDFTriage: Question Answering over Long, Structured Documents
Paper • 2309.08872 • Published • 55 -
StarCoder: may the source be with you!
Paper • 2305.06161 • Published • 34
safety
Scale
Evals
Fav papers
-
Large-Scale Automatic Audiobook Creation
Paper • 2309.03926 • Published • 55 -
Agents: An Open-source Framework for Autonomous Language Agents
Paper • 2309.07870 • Published • 43 -
PDFTriage: Question Answering over Long, Structured Documents
Paper • 2309.08872 • Published • 55 -
StarCoder: may the source be with you!
Paper • 2305.06161 • Published • 34
LLM Reasoning
-
Teaching Large Language Models to Reason with Reinforcement Learning
Paper • 2403.04642 • Published • 48 -
How Far Are We from Intelligent Visual Deductive Reasoning?
Paper • 2403.04732 • Published • 21 -
Common 7B Language Models Already Possess Strong Math Capabilities
Paper • 2403.04706 • Published • 18 -
DeepSeek-Prover: Advancing Theorem Proving in LLMs through Large-Scale Synthetic Data
Paper • 2405.14333 • Published • 47
safety
finetuning
Scale
VLMs