SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning Paper • 2606.13673 • Published Jun 11 • 112
AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents Paper • 2607.02255 • Published Jul 2 • 69
Rethinking Classifier-Free Guidance in On-Policy Diffusion Distillation Paper • 2607.24731 • Published Jul 27 • 80
SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs Paper • 2608.03573 • Published 27 days ago • 59
SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks Paper • 2608.02023 • Published about 1 month ago • 158
Zetta ζ: An Efficient Closed-Loop Embodied Harness for Self-Evolving Physical Intelligence Paper • 2608.16590 • Published 16 days ago • 149
SEAOTTER: Sensor Embedded Autoencoding with One-Time Transcode for Efficient Reconstruction Paper • 2606.03940 • Published Jun 2 • 5
Code2LoRA: Hypernetwork-Generated Adapters for Code Language Models under Software Evolution Paper • 2606.06492 • Published Jun 4 • 96
Towards Streaming Synchronized Spatial Audio Generation via Autoregressive Diffusion Transformer Paper • 2605.30940 • Published May 29 • 38
The Road Ahead in Autonomous Driving: The KITScenes Multimodal Dataset Paper • 2606.02956 • Published Jun 1 • 19
LoomVideo: Unifying Multimodal Inputs into Video Generation and Editing Paper • 2606.06042 • Published Jun 4 • 24