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
Runtime error
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
113
McGill-NLP/AfriE5-Large-instruct
Feature Extraction
•
0.6B
•
Updated
•
11
McGill-NLP/LLM2Vec-Qwen3-06B-mntp-supervised
Updated
McGill-NLP/LLM2Vec-Qwen3-17B-mntp-supervised
Updated
McGill-NLP/LLM2Vec-Qwen3-4B-mntp-supervised
Updated
McGill-NLP/LLM2Vec-Qwen3-8B-mntp-supervised
Updated
McGill-NLP/LLM2Vec-Qwen25-7B-Instruct-mntp-supervised
Updated
McGill-NLP/AfriqueLlama-8B
Text Generation
•
8B
•
Updated
•
21
McGill-NLP/AfriqueGemma-12B
Text Generation
•
12B
•
Updated
•
64
McGill-NLP/AfriqueGemma-4B
Text Generation
•
4B
•
Updated
•
58
McGill-NLP/AfriqueQwen-14B
Text Generation
•
15B
•
Updated
•
103
•
2
datasets
39
McGill-NLP/mgsm-pro
Viewer
•
Updated
•
40.5k
•
17
McGill-NLP/african_celtic_dataset
Viewer
•
Updated
•
57.5k
•
288
•
1
McGill-NLP/RealVQA-w_model_results_crag_mm_validation_50
Viewer
•
Updated
•
50
•
2
McGill-NLP/value-drifts
Viewer
•
Updated
•
10.6k
•
48
McGill-NLP/SSA-MT
Viewer
•
Updated
•
23.3k
•
8
McGill-NLP/SSA-MTE
Viewer
•
Updated
•
92.9k
•
77
•
2
McGill-NLP/openmath-filtered
Viewer
•
Updated
•
200k
•
47
•
1
McGill-NLP/WebLINX-full
Updated
•
4.29k
•
6
McGill-NLP/msteb_requests
Updated
•
1.08k
McGill-NLP/msteb_results
Updated
•
1.08k