Latest

Every published item, in order · 317 items
Oct 15
Oct 14
Oct 12
Oct 9
Oct 8
ProductsBuildersMulti-sourceSelected09:28
vLLM-Omni Technical Report: Unified Serving Runtime for Omni-Modality Generation

Serving stacks have so far been split between LLM servers optimized for autoregressive decode and diffusion stacks built for denoising, forcing teams to glue disjoint runtimes together in production. vLLM-Omni replaces that with one control plane supporting session-shaped, long-lived workloads like robot loops and world models. Engineers building multimodal assistants on Qwen3-Omni or MiniCPM-o should evaluate it against their current inference setups.

Event
arXiv: OpenAI@vLLM-Omni Team11 sourcesSource
Oct 7
Oct 6
Oct 5
Oct 2
PapersBuildersSelected10:41
Multi-Token Prediction Heads Research

This research significantly reduces the computational cost of implementing MTP heads, making advanced inference optimization more accessible. The findings could enable faster deployment of large language models without requiring massive pretraining resources. Developers and researchers working on model optimization can implement these techniques to improve throughput with minimal computational overhead.

arXiv: DeepSeek@Prachi Badarayani et al. (11)Source
Oct 1
PapersBuildersSelected09:58
Cross-World On-Policy Distillation for VLMs

This research addresses a critical gap in VLM distillation where students can match teacher outputs without relying on the same visual evidence. The CW-OPD method provides a corrective signal that makes visual evidence reliance explicit rather than implicit. Developers working with smaller models can leverage this approach to achieve performance comparable to much larger models while maintaining better visual grounding.

arXiv: DeepSeek@Yuanhao Sun et al. (5)Source
PapersBuildersSelected09:55
Activation-Conditioned Self-Distillation

ACSD provides a novel approach to token-level supervision throughout long responses by leveraging activation contrasts, offering a more stable alternative to existing methods. Researchers and developers working on reasoning models can implement this technique to improve mathematical accuracy without requiring reference solutions, potentially enhancing model performance across diverse training datasets.

arXiv: DeepSeek@Zhexi Lu et al. (5)Source