End-to-End Autoregressive Image Generation with 1D Semantic Tokenizer Paper • 2605.00503 • Published 4 days ago • 2
Map2World: Segment Map Conditioned Text to 3D World Generation Paper • 2605.00781 • Published 4 days ago • 10
GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents Paper • 2604.26752 • Published 6 days ago • 91
Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation Paper • 2604.24763 • Published 8 days ago • 68
For-Value: Efficient Forward-Only Data Valuation for finetuning LLMs and VLMs Paper • 2508.10180 • Published 10 days ago • 17
GTA-2: Benchmarking General Tool Agents from Atomic Tool-Use to Open-Ended Workflows Paper • 2604.15715 • Published 18 days ago • 3
Learning Adaptive Reasoning Paths for Efficient Visual Reasoning Paper • 2604.14568 • Published 19 days ago • 8
Cut Your Losses! Learning to Prune Paths Early for Efficient Parallel Reasoning Paper • 2604.16029 • Published 18 days ago • 23
Accelerating Speculative Decoding with Block Diffusion Draft Trees Paper • 2604.12989 • Published 21 days ago • 6
KnowRL: Boosting LLM Reasoning via Reinforcement Learning with Minimal-Sufficient Knowledge Guidance Paper • 2604.12627 • Published 21 days ago • 100
Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe Paper • 2604.13016 • Published 21 days ago • 88
Liquid Claude Collection Liquid Claude is a small series of LiquidAI/LFM2.5-1.2B-Thinking model that have been fine tuned on Claude chats/data. • 5 items • Updated 2 days ago • 2
Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models Paper • 2411.04996 • Published Nov 7, 2024 • 51