arXiv:2603.28760v1 Announce Type: new
Abstract: Accurate 3D understanding of human hands and objects during manipulation remains a significant challenge for egocentric computer vision. Existing hand-object interaction datasets are predominantly captur…
Anthropic didn’t intend to introduce Mythos this way. Details of what it calls its most capable AI model yet surfaced through a data leak in its content management system (CMS), revealing a LLM with sharply improved reasoning and…
Microsoft has reportedly had a hard time convincing corporate customers to pay premium prices for its enterprise AI products, particularly as their employees prefer ChatGPT or Gemini. The Information reported in December that Mic…
arXiv:2603.26483v1 Announce Type: new
Abstract: Privacy-preserving medical inference must balance data locality, diagnostic reliability, and deployment efficiency. This paper presents EcoFair, a simulated vertically partitioned inference framework for…
arXiv:2603.26575v1 Announce Type: new
Abstract: Climbing is a multifaceted sport that combines physical demands and emotional and cognitive challenges. Ascent styles differ in fall distance with lead climbing involving larger falls than top rope climb…
arXiv:2603.26595v1 Announce Type: new
Abstract: PQuantML is a new open-source, hardware-aware neural network model compression library tailored to end-to-end workflows. Motivated by the need to deploy performant models to environments with strict late…
arXiv:2603.26629v1 Announce Type: new
Abstract: Multimodal fusion requires integrating information from multiple sources that may conflict depending on context. Existing fusion approaches typically rely on static assumptions about source reliability, …
arXiv:2509.24779v3 Announce Type: replace
Abstract: Molecular Dynamics (MD) is a powerful computational microscope for probing protein functions. However, the need for fine-grained integration and the long timescales of biomolecular events make MD com…
arXiv:2511.14510v2 Announce Type: replace
Abstract: During LLM inference, KVCache memory usage grows linearly with sequence length and batch size and often exceeds GPU capacity. Recent proposals offload KV states to host memory and reduce transfers us…
arXiv:2602.11937v2 Announce Type: replace
Abstract: Reasoning-focused LLMs improve answer quality by generating longer reasoning traces, but the additional tokens dramatically increase serving cost, motivating inference optimization. We extend and app…