Blind Men and the Elephant: Probing the Epistemic Myopia of LLMs under Long-Tail Divergent Knowledge
🤝 Open to Collab
Junrulu
Junrulu
AI & ML interests
None yet
Recent Activity
View all activity
Organizations
Sparse Sparse Attention by Aligning Full and Sparse Attention Outputs in Feature Space
A Fine-Grained Composite Benchmark for Role-Playing and Instruction-Following
Tuning LLMs to Use Memos for Consistent Long-Range Open-Domain Conversation
Teaching Agents for Proactive Context Management via Fine-grained RL
-
tencent/ContextPilot-E4B
Text Generation • 8B • Updated • 962 • 8 -
tencent/ContextPilot-8B
Text Generation • 8B • Updated • 788 • 11 -
tencent/ContextPilot-14B
Text Generation • 15B • Updated • 1.02k • 23 -
ContextPilot: Teaching Agents for Proactive Context Management via Fine-grained RL
Paper • 2608.28476 • Published • 27
Unlocking the Native Agentic Potential for Lightweight Large Language Models
-
tencent/Youtu-LLM-2B
Text Generation • 2B • Updated • 11.4k • 231 -
tencent/Youtu-LLM-2B-Base
Text Generation • 2B • Updated • 2.07k • 43 -
tencent/Youtu-LLM-2B-GGUF
Text Generation • 2B • Updated • 742 • 30 -
Youtu-LLM: Unlocking the Native Agentic Potential for Lightweight Large Language Models
Paper • 2512.24618 • Published • 156
Eliminating Biased Length Reliance of Direct Preference Optimization via Down-Sampled KL Divergence
-
jiazhengli/Pythia-2.8B-HH-RLHF-Iterative-SamPO
Text Generation • 3B • Updated • 20 -
jiazhengli/Pythia-2.8B-TLDR-Iterative-SamPO
Text Generation • 3B • Updated • 25 -
Junrulu/Llama-3-8B-Instruct-Iterative-SamPO
Text Generation • 8B • Updated • 13 • 1 -
Eliminating Biased Length Reliance of Direct Preference Optimization via Down-Sampled KL Divergence
Paper • 2406.10957 • Published • 2
Blind Men and the Elephant: Probing the Epistemic Myopia of LLMs under Long-Tail Divergent Knowledge
Teaching Agents for Proactive Context Management via Fine-grained RL
-
tencent/ContextPilot-E4B
Text Generation • 8B • Updated • 962 • 8 -
tencent/ContextPilot-8B
Text Generation • 8B • Updated • 788 • 11 -
tencent/ContextPilot-14B
Text Generation • 15B • Updated • 1.02k • 23 -
ContextPilot: Teaching Agents for Proactive Context Management via Fine-grained RL
Paper • 2608.28476 • Published • 27
Sparse Sparse Attention by Aligning Full and Sparse Attention Outputs in Feature Space
Unlocking the Native Agentic Potential for Lightweight Large Language Models
-
tencent/Youtu-LLM-2B
Text Generation • 2B • Updated • 11.4k • 231 -
tencent/Youtu-LLM-2B-Base
Text Generation • 2B • Updated • 2.07k • 43 -
tencent/Youtu-LLM-2B-GGUF
Text Generation • 2B • Updated • 742 • 30 -
Youtu-LLM: Unlocking the Native Agentic Potential for Lightweight Large Language Models
Paper • 2512.24618 • Published • 156
A Fine-Grained Composite Benchmark for Role-Playing and Instruction-Following
Eliminating Biased Length Reliance of Direct Preference Optimization via Down-Sampled KL Divergence
-
jiazhengli/Pythia-2.8B-HH-RLHF-Iterative-SamPO
Text Generation • 3B • Updated • 20 -
jiazhengli/Pythia-2.8B-TLDR-Iterative-SamPO
Text Generation • 3B • Updated • 25 -
Junrulu/Llama-3-8B-Instruct-Iterative-SamPO
Text Generation • 8B • Updated • 13 • 1 -
Eliminating Biased Length Reliance of Direct Preference Optimization via Down-Sampled KL Divergence
Paper • 2406.10957 • Published • 2
Tuning LLMs to Use Memos for Consistent Long-Range Open-Domain Conversation