Kye Gomez

kye's activity

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

upvoted 9 papers 2 days ago

Multimodal Fact-Level Attribution for Verifiable Reasoning

Paper • 2602.11509 • Published 4 days ago • 3

MiniCPM-SALA: Hybridizing Sparse and Linear Attention for Efficient Long-Context Modeling

Paper • 2602.11761 • Published 4 days ago • 5

ThinkRouter: Efficient Reasoning via Routing Thinking between Latent and Discrete Spaces

Paper • 2602.11683 • Published 4 days ago • 6

Adapting Vision-Language Models for E-commerce Understanding at Scale

Paper • 2602.11733 • Published 4 days ago • 10

DeepSight: An All-in-One LM Safety Toolkit

Paper • 2602.12092 • Published 3 days ago • 12

dVoting: Fast Voting for dLLMs

Paper • 2602.12153 • Published 3 days ago • 19

DeepGen 1.0: A Lightweight Unified Multimodal Model for Advancing Image Generation and Editing

Paper • 2602.12205 • Published 3 days ago • 73

MOSS-Audio-Tokenizer: Scaling Audio Tokenizers for Future Audio Foundation Models

Paper • 2602.10934 • Published 4 days ago • 47

The Devil Behind Moltbook: Anthropic Safety is Always Vanishing in Self-Evolving AI Societies

Paper • 2602.09877 • Published 5 days ago • 184

upvoted 3 papers 3 days ago

LawThinker: A Deep Research Legal Agent in Dynamic Environments

Paper • 2602.12056 • Published 3 days ago • 31

GigaBrain-0.5M*: a VLA That Learns From World Model-Based Reinforcement Learning

Paper • 2602.12099 • Published 3 days ago • 48

Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation

Paper • 2602.12125 • Published 3 days ago • 56

upvoted 4 papers 4 days ago

AgenticPay: A Multi-Agent LLM Negotiation System for Buyer-Seller Transactions

Paper • 2602.06008 • Published 10 days ago • 4

Towards Autonomous Mathematics Research

Paper • 2602.10177 • Published 5 days ago • 33

Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters

Paper • 2602.10604 • Published 5 days ago • 174

G-LNS: Generative Large Neighborhood Search for LLM-Based Automatic Heuristic Design

Paper • 2602.08253 • Published 7 days ago • 25

upvoted 4 papers 6 days ago

Vision Transformer Finetuning Benefits from Non-Smooth Components

Paper • 2602.06883 • Published 9 days ago • 4

ReMiT: RL-Guided Mid-Training for Iterative LLM Evolution

Paper • 2602.03075 • Published 13 days ago • 6

OmniMoE: An Efficient MoE by Orchestrating Atomic Experts at Scale

Paper • 2602.05711 • Published 10 days ago • 9

OmniVideo-R1: Reinforcing Audio-visual Reasoning with Query Intention and Modality Attention

Paper • 2602.05847 • Published 10 days ago • 12