Thomas Ferraz

thomas-ferraz's activity

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

upvoted 3 papers 27 days ago

MemMA: Coordinating the Memory Cycle through Multi-Agent Reasoning and In-Situ Self-Evolution

Paper • 2603.18718 • Published Mar 19 • 10

Voxtral TTS

Paper • 2603.25551 • Published 29 days ago • 59

MSA: Memory Sparse Attention for Efficient End-to-End Memory Model Scaling to 100M Tokens

Paper • 2603.23516 • Published Mar 6 • 48

upvoted 2 papers 3 months ago

ConceptMoE: Adaptive Token-to-Concept Compression for Implicit Compute Allocation

Paper • 2601.21420 • Published Jan 29 • 42

KaVa: Latent Reasoning via Compressed KV-Cache Distillation

Paper • 2510.02312 • Published Oct 2, 2025 • 3

upvoted a collection 4 months ago

Gemma 3 Release

Collection

28 items • Updated Mar 12 • 635

upvoted an article 6 months ago

view article

Article

mem-agent: Equipping LLM Agents with Memory Using RL

• 

Oct 9, 2025

•

33

upvoted an article about 1 year ago

view article

Article

Provence: efficient and robust context pruning for retrieval-augmented generation

• 

Jan 28, 2025

•

25

upvoted 2 papers about 1 year ago

ReasonFlux: Hierarchical LLM Reasoning via Scaling Thought Templates

Paper • 2502.06772 • Published Feb 10, 2025 • 22

FastKV: Decoupling of Context Reduction and KV Cache Compression for Prefill-Decoding Acceleration

Paper • 2502.01068 • Published Feb 3, 2025 • 18

upvoted 2 collections about 1 year ago

mHuBERT-147 models

Collection

Compact yet powerful multilingual speech representation models based on the HuBERT architecture. • 3 items • Updated Jun 4, 2024 • 8

EuroLLM

Collection

14 items • Updated Feb 6 • 45

upvoted 2 papers over 1 year ago

LLM Self-Correction with DeCRIM: Decompose, Critique, and Refine for Enhanced Following of Instructions with Multiple Constraints

Paper • 2410.06458 • Published Oct 9, 2024 • 8

mHuBERT-147: A Compact Multilingual HuBERT Model

Paper • 2406.06371 • Published Jun 10, 2024 • 7

upvoted a collection over 2 years ago

Multilingual DistilWhisper

Collection

Multilingual Distilwhisper allows for better ASR performance in target languages by adding lightweight CLSR modules on top of whisper-small. • 3 items • Updated Mar 18, 2024 • 6

upvoted 2 papers over 2 years ago

DistilWhisper: Efficient Distillation of Multi-task Speech Models via Language-Specific Experts

Paper • 2311.01070 • Published Nov 2, 2023 • 3

ZeroBERTo: Leveraging Zero-Shot Text Classification by Topic Modeling

Paper • 2201.01337 • Published Jan 4, 2022 • 2