Token Assorted: Mixing Latent and Text Tokens for Improved Language Model Reasoning
Paper
•
2502.03275
•
Published
•
2
•
1
AK
akhaliq
AI & ML interests
None yet
Recent Activity
commented on
a paper
about 8 hours ago
Token Assorted: Mixing Latent and Text Tokens for Improved Language
Model Reasoning
commented on
a paper
about 8 hours ago
LIMO: Less is More for Reasoning
commented on
a paper
about 8 hours ago
SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language
Model
Organizations
akhaliq's activity
commented
3
papers
about 8 hours ago
commented
a
paper
1 day ago
commented
5
papers
2 days ago
OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Models
Paper
•
2502.01061
•
Published
•
149
•
16
ZebraLogic: On the Scaling Limits of LLMs for Logical Reasoning
Paper
•
2502.01100
•
Published
•
12
•
2
The Jumping Reasoning Curve? Tracking the Evolution of Reasoning Performance in GPT-[n] and o-[n] Models on Multimodal Puzzles
Paper
•
2502.01081
•
Published
•
9
•
2
Scaling Embedding Layers in Language Models
Paper
•
2502.01637
•
Published
•
16
•
3
Improving Transformer World Models for Data-Efficient RL
Paper
•
2502.01591
•
Published
•
8
•
2
commented
4
papers
3 days ago
MatAnyone: Stable Video Matting with Consistent Memory Propagation
Paper
•
2501.14677
•
Published
•
26
•
2
Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming
Paper
•
2501.18837
•
Published
•
7
•
5
s1: Simple test-time scaling
Paper
•
2501.19393
•
Published
•
88
•
8
Trading Inference-Time Compute for Adversarial Robustness
Paper
•
2501.18841
•
Published
•
3
•
2
commented
2
papers
6 days ago
commented
3
papers
7 days ago
Atla Selene Mini: A General Purpose Evaluation Model
Paper
•
2501.17195
•
Published
•
30
•
4
Early External Safety Testing of OpenAI's o3-mini: Insights from the Pre-Deployment Evaluation
Paper
•
2501.17749
•
Published
•
12
•
2
TAID: Temporally Adaptive Interpolated Distillation for Efficient Knowledge Transfer in Language Models
Paper
•
2501.16937
•
Published
•
4
•
2
commented
2
papers
8 days ago