Reformulating the RL of reasoning LLMs through Markovian Thinking paradigm.
AI & ML interests
computational linguistics, natural language processing
Recent Activity
Papers
Value Drifts: Tracing Value Alignment During LLM Post-Training
LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders
spaces
7
pinned
Running
6
AfroBench
🥇
Comprehensive benchmark of LLMs on African Languages
pinned
Restarting
1
mSTEB Leaderboard
🥇
Leaderboard for mSTEB benchmark
pinned
Running
17
WebLINX Explorer
😻
Visualize web interaction recordings
Runtime error
3
Agent Reward Bench Leaderboard
🥇
Leaderboard for AgentRewardBench
Running
5
Agent Reward Bench Demo
💻
Explore agent trajectories and judgments in web benchmarks
Running
3
Safearena Leaderboard
🏃
SafeArena Leaderboard
models
107
McGill-NLP/AfriqueLlama-8B
Text Generation
•
8B
•
Updated
•
20
McGill-NLP/AfriqueGemma-12B
Text Generation
•
12B
•
Updated
•
22
McGill-NLP/AfriqueGemma-4B
Text Generation
•
4B
•
Updated
•
28
McGill-NLP/AfriqueQwen-14B
Text Generation
•
15B
•
Updated
•
62
•
2
McGill-NLP/AfriqueQwen-8B
Text Generation
•
8B
•
Updated
•
17
•
1
McGill-NLP/LLM2Vec-Qwen3-8B-uni-simcse
Updated
McGill-NLP/LLM2Vec-Qwen3-4B-uni-simcse
Updated
McGill-NLP/LLM2Vec-Qwen3-17B-uni-simcse
Updated
McGill-NLP/LLM2Vec-Qwen3-06B-uni-simcse
Updated
McGill-NLP/LLM2Vec-Qwen25-7B-Instruct-uni-simcse
Updated
datasets
37
McGill-NLP/RealVQA-w_model_results_crag_mm_validation_50
Viewer
•
Updated
•
50
•
1
McGill-NLP/value-drifts
Viewer
•
Updated
•
10.6k
•
4
McGill-NLP/SSA-MT
Viewer
•
Updated
•
23.3k
•
21
McGill-NLP/SSA-MTE
Viewer
•
Updated
•
92.9k
•
283
•
2
McGill-NLP/openmath-filtered
Viewer
•
Updated
•
200k
•
63
•
1
McGill-NLP/WebLINX-full
Updated
•
7.1k
•
6
McGill-NLP/msteb_requests
Updated
•
1.41k
McGill-NLP/msteb_results
Updated
•
1.41k
McGill-NLP/GlobalNLI
Viewer
•
Updated
•
37.2k
•
191
McGill-NLP/WebMMU
Viewer
•
Updated
•
4.24k
•
118
•
1