BEAR: Benchmarking and Enhancing Multimodal Language Models for Atomic Embodied Capabilities Paper • 2510.08759 • Published Oct 9, 2025 • 47
LLMs Learn to Deceive Unintentionally: Emergent Misalignment in Dishonesty from Misaligned Samples to Biased Human-AI Interactions Paper • 2510.08211 • Published Oct 9, 2025 • 22
LongLive: Real-time Interactive Long Video Generation Paper • 2509.22622 • Published Sep 26, 2025 • 187
Kling-Avatar: Grounding Multimodal Instructions for Cascaded Long-Duration Avatar Animation Synthesis Paper • 2509.09595 • Published Sep 11, 2025 • 48
FLUX-Reason-6M & PRISM-Bench: A Million-Scale Text-to-Image Reasoning Dataset and Comprehensive Benchmark Paper • 2509.09680 • Published Sep 11, 2025 • 43
T2I-ReasonBench: Benchmarking Reasoning-Informed Text-to-Image Generation Paper • 2508.17472 • Published Aug 24, 2025 • 26
Go to Zero: Towards Zero-shot Motion Generation with Million-scale Data Paper • 2507.07095 • Published Jul 9, 2025 • 56