MBD-LMs Collection https://sjtu-deng-lab.github.io/mbd-lms/ • 9 items • Updated about 7 hours ago • 2
World-Language-Action Model for Unified World Modeling, Language Reasoning, and Action Synthesis Paper • 2606.05979 • Published 23 days ago • 8
LatentUM: Unleashing the Potential of Interleaved Cross-Modal Reasoning via a Latent-Space Unified Model Paper • 2604.02097 • Published Apr 2 • 32 • 4
LatentUM: Unleashing the Potential of Interleaved Cross-Modal Reasoning via a Latent-Space Unified Model Paper • 2604.02097 • Published Apr 2 • 32
Think-Then-Generate: Reasoning-Aware Text-to-Image Diffusion with LLM Encoders Paper • 2601.10332 • Published Jan 15 • 32
LiveTalk: Real-Time Multimodal Interactive Video Diffusion via Improved On-Policy Distillation Paper • 2512.23576 • Published Dec 29, 2025 • 66
LoPA: Scaling dLLM Inference via Lookahead Parallel Decoding Paper • 2512.16229 • Published Dec 18, 2025 • 17
Fast and Accurate Causal Parallel Decoding using Jacobi Forcing Paper • 2512.14681 • Published Dec 16, 2025 • 44
DEER: Draft with Diffusion, Verify with Autoregressive Models Paper • 2512.15176 • Published Dec 17, 2025 • 45
Mantis: A Versatile Vision-Language-Action Model with Disentangled Visual Foresight Paper • 2511.16175 • Published Nov 20, 2025 • 12
Efficient Long-context Language Model Training by Core Attention Disaggregation Paper • 2510.18121 • Published Oct 20, 2025 • 124
NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale Paper • 2508.10711 • Published Aug 14, 2025 • 146
Running on Zero Agents 4 D2F LLaDA Instruct 8B 👁 4 Diffusion LLMs Can Do Faster-Than-AR Inference via Discret
Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing Paper • 2508.09192 • Published Aug 8, 2025 • 31
Running on Zero Agents 4 D2F LLaDA Instruct 8B 👁 4 Diffusion LLMs Can Do Faster-Than-AR Inference via Discret
Scaling Speculative Decoding with Lookahead Reasoning Paper • 2506.19830 • Published Jun 24, 2025 • 13