cập nhật 6 phút trước

⏱ Độ trễ thật của tab này: trung bình 7.3 giờ sau khi CVE được công bố (n = 5338, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.

21
MMFlash: Faster Speculative Decoding for Vision-Language Models
📄 Paper HF Daily Papers 4 ngày trước

Speculative decoding accelerates generation by letting a lightweight drafter propose tokens for parallel verification by a target model. Diffusion drafters such as DFlash propose an entire token block in a single forward pass, but mainly focus on text-only tasks, leaving multimod…

🅲 hạng C
21
TTB: Test-time Baking for Efficient Rendering of Decoder-only View Synthesis Models
📄 Paper HF Daily Papers 5 ngày trước

Decoder-only Large View Synthesis Models (LVSMs) with KV-cache have recently achieved state-of-the-art quality by regressing novel views from neural networks without reconstructing 3D geometry, while Test-Time Training (TTT) layers save computation but sacrifice quality. We propo…

🅲 hạng C
20
SO-Arena: Benchmarking the Capability Spectrum and Reliability of System One Models
📄 Paper HF Daily Papers 6 ngày trước

System One models promise fast, general-purpose decision-making without lengthy token generation. However, understanding their capability spectrum and decision reliability requires more than aggregate performance on current benchmarks. Existing evaluations often provide limited i…

🅲 hạng C
20
Factored One-sided Adam-Moment for Practical and Scalable SOAP
📄 Paper HF Daily Papers 5 ngày trước

Second-order optimizers (e.g., Shampoo, SOAP) have emerged as compelling alternatives to Adam/AdamW and promise faster per-step convergence than AdamW in transformer training. However, they still remain costly in practice, and even SOAP still pays substantial optimizer-state memo…

🅲 hạng C
20
The Value of Thinking: Learning When to Reason in Hybrid Decision Models
📄 Paper HF Daily Papers 5 ngày trước

Existing adaptive-reasoning methods shorten the explicit reasoning a model writes, or skip it by switching modes; either way the answer is still written out token by token. Rather than deciding how much to think, we explore a different paradigm, zero-or-T thinking: a single model…

🅲 hạng C