Tom Spis

Pom-Pom-Tom's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 2 months ago

Softpick: No Attention Sink, No Massive Activations with Rectified Softmax

Paper • 2504.20966 • Published Apr 29 • 32

upvoted an article 2 months ago

view article

Article

Introduction to State Space Models (SSM)

• 

Jul 19, 2024

•

195

upvoted 18 papers 3 months ago

A Survey of Reinforcement Learning for Large Reasoning Models

Paper • 2509.08827 • Published Sep 10 • 189

Towards a Unified View of Large Language Model Post-Training

Paper • 2509.04419 • Published Sep 4 • 75

Behavioral Fingerprinting of Large Language Models

Paper • 2509.04504 • Published Sep 2 • 5

Set Block Decoding is a Language Model Inference Accelerator

Paper • 2509.04185 • Published Sep 4 • 52

Symbolic Graphics Programming with Large Language Models

Paper • 2509.05208 • Published Sep 5 • 46

Why Language Models Hallucinate

Paper • 2509.04664 • Published Sep 4 • 193

LLM-based Optimization of Compound AI Systems: A Survey

Paper • 2410.16392 • Published Oct 21, 2024 • 16

Retrieval-augmented reasoning with lean language models

Paper • 2508.11386 • Published Aug 15 • 5

Advances in Speech Separation: Techniques, Challenges, and Future Trends

Paper • 2508.10830 • Published Aug 14 • 14

Mind the Generation Process: Fine-Grained Confidence Estimation During LLM Generation

Paper • 2508.12040 • Published Aug 16 • 14

Evaluating Podcast Recommendations with Profile-Aware LLM-as-a-Judge

Paper • 2508.08777 • Published Aug 12 • 15

Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL

Paper • 2508.13167 • Published Aug 6 • 129

Refining Contrastive Learning and Homography Relations for Multi-Modal Recommendation

Paper • 2508.13745 • Published Aug 19 • 1

mSCoRe: a Multilingual and Scalable Benchmark for Skill-based Commonsense Reasoning

Paper • 2508.10137 • Published Aug 13 • 2

Leuvenshtein: Efficient FHE-based Edit Distance Computation with Single Bootstrap per Cell

Paper • 2508.14568 • Published Aug 20 • 2

Dissecting Tool-Integrated Reasoning: An Empirical Study and Analysis

Paper • 2508.15754 • Published Aug 21 • 4

On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting

Paper • 2508.11408 • Published Aug 15 • 8

Quantization Meets dLLMs: A Systematic Study of Post-training Quantization for Diffusion LLMs

Paper • 2508.14896 • Published Aug 20 • 22