Tom Spis

Pom-Pom-Tom's activity

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

upvoted a paper 1 day ago

LLM-based Optimization of Compound AI Systems: A Survey

Paper • 2410.16392 • Published Oct 21, 2024 • 17

upvoted 17 papers 4 days ago

Retrieval-augmented reasoning with lean language models

Paper • 2508.11386 • Published 23 days ago • 5

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

Paper • 2508.10830 • Published 24 days ago • 13

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

Paper • 2508.12040 • Published 22 days ago • 14

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

Paper • 2508.08777 • Published 26 days ago • 15

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

Paper • 2508.13167 • Published Aug 6 • 123

Refining Contrastive Learning and Homography Relations for Multi-Modal Recommendation

Paper • 2508.13745 • Published 19 days ago • 1

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

Paper • 2508.10137 • Published 25 days ago • 2

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

Paper • 2508.14568 • Published 18 days ago • 2

Dissecting Tool-Integrated Reasoning: An Empirical Study and Analysis

Paper • 2508.15754 • Published 17 days ago • 4

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

Paper • 2508.11408 • Published 23 days ago • 7

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

Paper • 2508.14896 • Published 18 days ago • 21

NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model

Paper • 2508.14444 • Published 18 days ago • 35

From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery

Paper • 2508.14111 • Published 20 days ago • 32

DuPO: Enabling Reliable LLM Self-Verification via Dual Preference Optimization

Paper • 2508.14460 • Published 18 days ago • 80

LiveMCP-101: Stress Testing and Diagnosing MCP-enabled Agents on Challenging Queries

Paper • 2508.15760 • Published 17 days ago • 44

CARFT: Boosting LLM Reasoning via Contrastive Learning with Annotated Chain-of-Thought-based Reinforced Fine-Tuning

Paper • 2508.15868 • Published 18 days ago • 3

InMind: Evaluating LLMs in Capturing and Applying Individual Human Reasoning Styles

Paper • 2508.16072 • Published 17 days ago • 3

upvoted 2 papers 5 days ago

AgentFly: Fine-tuning LLM Agents without Fine-tuning LLMs

Paper • 2508.16153 • Published 16 days ago • 132

If We May De-Presuppose: Robustly Verifying Claims through Presupposition-Free Question Decomposition

Paper • 2508.16838 • Published 16 days ago • 1