Decode Before You Hear: Speculative Listening for Chunk-Interleaved Full-Duplex Speech Language Models Paper • 2611.06982 • Published 8 days ago • 12
Random Is Almost Enough? Stable and Low-Cost Benchmark Compression via BestRand Paper • 2611.00883 • Published 12 days ago • 53
Factorized MLLM Embeddings for Composed Image Retrieval Paper • 2611.05193 • Published 9 days ago • 48
SpecPilot: Autonomous Algorithm Discovery and Systems Optimization for Speculative Decoding Paper • 2611.02501 • Published 10 days ago • 21
OSWAM: An Effective World Action Model with One-Step Action Generation Paper • 2610.35850 • Published 17 days ago • 12
SpecOPD: Branch-Parallel On-Policy Distillation for Speculative Decoding Paper • 2611.02846 • Published 10 days ago • 16
How I Aligned Your Model: Scaling Up Multilingual Safety Training with Templates Paper • 2610.40516 • Published 14 days ago • 11
Auto-Research Agent on MSA Organization to Improve Protein-Protein Complex Structure Prediction Paper • 2611.03183 • Published 9 days ago • 3
GLOW-FM: Efficient Generative Low-Light Image Enhancement with One-Step Latent Flow Matching Paper • 2610.31222 • Published 20 days ago • 14
Look Only When Needed: Certificate-Guided Visual Routing for Efficient Diffusion VLMs Paper • 2610.36671 • Published 16 days ago • 117
On the SPOT: Enhancing Speculative Decoding for Diffusion Language Models via Commit-Order Prediction Paper • 2610.22543 • Published 17 days ago • 29
ChronoReplay: One Answer Interface Is Not Enough for Streaming Spatial Intelligence Paper • 2610.34283 • Published 18 days ago • 40
Building Auditable AI Text Detectors with Sparse Autoencoders Paper • 2610.30006 • Published 22 days ago • 14
Factorization-Guided Training and Inference for Diffusion-Drafted Speculative Decoding Paper • 2610.23935 • Published Oct 7 • 8
Making MLLM Latents Matter: Factor-Aware Predictive Learning for Cinematic Video Generation Paper • 2610.30926 • Published 20 days ago • 29
Automating ML for Science: Can Frontier Agents Climb Scientific Hills in the Wild? Paper • 2610.28763 • Published 23 days ago • 19
Specter: Fast MoE Inference via Quantization-Enabled Multi-Step Speculative Offloading Paper • 2511.14102 • Published 23 days ago • 23