Reformulating the RL of reasoning LLMs through Markovian Thinking paradigm.
AI & ML interests
computational linguistics, natural language processing
Recent Activity
View all activity
Papers
Value Drifts: Tracing Value Alignment During LLM Post-Training
LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders
spaces
7
pinned
Running
5
AfroBench
🥇
Comprehensive benchmark of LLMs on African Languages
pinned
Running
1
mSTEB Leaderboard
🥇
Leaderboard for mSTEB benchmark
pinned
Running
17
WebLINX Explorer
😻
Visualize web interaction recordings
Running
3
Agent Reward Bench Leaderboard
🥇
Leaderboard for AgentRewardBench
Running
4
Agent Reward Bench Demo
💻
Explore agent trajectories and judgments in web benchmarks
Sleeping
3
Safearena Leaderboard
🏃
SafeArena Leaderboard
models
75
McGill-NLP/LLM2Vec-Meta-Llama-32-3B-Instruct-mntp
Updated
•
30
McGill-NLP/LLM2Vec-Meta-Llama-32-3B-Instruct-mntp-supervised
Updated
McGill-NLP/longcot-8k-1.5b
2B
•
Updated
•
5
McGill-NLP/delethink-24k-1.5b
2B
•
Updated
•
535
•
5
McGill-NLP/delethink-96k-1.5b
2B
•
Updated
•
10
•
3
McGill-NLP/longcot-24k-1.5b
2B
•
Updated
•
151
•
1
McGill-NLP/delethink-96k-base-1.5b
2B
•
Updated
•
2
•
1
McGill-NLP/ssa-comet-mtl-final
Updated
McGill-NLP/ssa-comet-stl-final
Updated
McGill-NLP/ssa-comet-qe-final
Updated
datasets
36
McGill-NLP/value-drifts
Viewer
•
Updated
•
10.6k
•
66
McGill-NLP/SSA-MT
Viewer
•
Updated
•
23.3k
•
36
McGill-NLP/SSA-MTE
Viewer
•
Updated
•
92.9k
•
138
•
2
McGill-NLP/openmath-filtered
Viewer
•
Updated
•
200k
•
110
McGill-NLP/WebLINX-full
Updated
•
12k
•
6
McGill-NLP/msteb_requests
Updated
•
1.11k
McGill-NLP/msteb_results
Updated
•
1.04k
McGill-NLP/GlobalNLI
Viewer
•
Updated
•
37.2k
•
103
McGill-NLP/WebMMU
Viewer
•
Updated
•
4.24k
•
110
•
1
McGill-NLP/AdvBench-IR-Small-Wiki-100
Viewer
•
Updated
•
50.9k
•
52