Search: “routing”

arXiv:2608.00097v1 Announce Type: cross Abstract: Physical learning rules such as equilibrium propagation (EP), coupled learning (CL), and adjoint coupled learning (AL) train resistive networks throug

arXiv:2607.11510v2 Announce Type: replace Abstract: Causal discovery from observational tabular data remains fundamentally challenging, primarily due to the heterogeneity of underlying causal mechanis

I've been working on speeding up DeepSeek-V4-Flash-0731 in Krasis and have now got the long-prompt prefill quite a bit faster on a single RTX PRO 6000 96GB. These are timing-disabled internal Krasis r

arXiv:2608.00547v1 Announce Type: new Abstract: Contact-rich manipulation remains challenging because successful control depends on physical interaction cues that are often weakly observable from visi

arXiv:2608.02497v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models excel in robotic manipulation but suffer catastrophic performance drops when canonical instructions are simply parap

arXiv:2608.02124v1 Announce Type: cross Abstract: Vision-language models (VLMs) remain unreliable when predictions require fine-grained visual evidence. We identify a previously overlooked cause: spec

When people think about digital transformation in banking, they often focus on the visible results: mobile apps and new digital services. But there's an invisible infrastructure making all these servi

arXiv:2608.00588v1 Announce Type: new Abstract: Layout-to-image diffusion models have achieved impressive semantic controllability by conditioning generation on category-level segmentation maps. Howev

arXiv:2608.00569v1 Announce Type: new Abstract: Deploying billion-parameter Vision-Language-Action (VLA) policies on mobile robots creates a systems conflict: semantic reasoning benefits from cloud GP

arXiv:2608.00975v1 Announce Type: new Abstract: Large vision--language models (VLMs) can reason step by step about complex visual scenes, but this open-ended, autoregressive chain-of-thought (CoT) app

arXiv:2602.11565v5 Announce Type: replace Abstract: Efficient domain adaptation remains a fundamental challenge for deploying multi-agent systems across diverse environments in Vehicle-to-Everything (

arXiv:2608.02091v1 Announce Type: new Abstract: A bfloat16 transformer can train normally for many steps and then collapse abruptly. Distinct low-precision errors can trigger the same failure, leaving

arXiv:2608.01060v1 Announce Type: new Abstract: Cross-view geo-localization (CVGL) retrieves geo-tagged satellite imagery for a ground-view query. Most systems exhaustively search a flat, fixed-resolu

arXiv:2608.01616v1 Announce Type: new Abstract: Competitive analysis is central to the study of online algorithms, but upper bounds are often highly problem-specific. We develop a more unifying method

arXiv:2608.02129v1 Announce Type: new Abstract: In-context learning (ICL) has attracted increasing attention for enabling models to perform new tasks using only a few ``input--output'' prompt examples

arXiv:2602.07086v2 Announce Type: replace-cross Abstract: Enterprise software systems commonly expose business functionality through both relational databases and REST APIs. Accessing these interfaces

arXiv:2608.00574v1 Announce Type: new Abstract: Vision-language MoE batches contain different numbers of image and text tokens. Image resolution, image count, tiling, and prompt length all change this

arXiv:2608.01630v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) improves factuality but adds latency and engineering overhead at serving time. We propose RING (Retrieval-Internali

arXiv:2601.10588v2 Announce Type: replace-cross Abstract: Whether neural information processing is entirely classical or involves quantum-mechanical elements remains an open question. Here we propose

arXiv:2608.01434v1 Announce Type: new Abstract: Normally the statistical mechanics of learning treats constraints on weight distributions as restrictions that shrink the space of possible solutions. T

arXiv:2608.01839v1 Announce Type: new Abstract: Transcranial focused ultrasound (tFUS) requires accurate estimation of the intracranial acoustic field, which is distorted by skull-induced aberrations.

arXiv:2608.02080v1 Announce Type: new Abstract: Whole-body tactile sensing is a prerequisite for humanoids that operate in contact-rich human environments, but conventional taxel arrays scale poorly w

arXiv:2608.02415v1 Announce Type: new Abstract: Intent classification in Large Language Models (LLMs) involves categorizing user prompts into predefined classes. For instance, given a user prompt, the

arXiv:2608.00419v1 Announce Type: cross Abstract: Large language models deployed in real-time, regulated settings face knowledge staleness, catastrophic forgetting, hallucination, and weak feedback lo

arXiv:2608.00220v1 Announce Type: cross Abstract: We show that on-policy reinforcement learning with verifiable rewards (RLVR) can improve the current objective while making successful behaviors for l

arXiv:2607.28662v1 Announce Type: new Abstract: Large language models extract entities and relationships from unstructured documents fluently but inconsistently: type vocabularies fracture across docu

arXiv:2607.29440v1 Announce Type: new Abstract: Long-term multimodal memory must support not only retrieving relevant information but also computing over observations accumulated across interactions.

arXiv:2606.13303v2 Announce Type: replace Abstract: Recent diffusion editors perform diverse instruction-based edits while conditioning on the source image at every denoising step. Yet persistent sour

arXiv:2603.11872v3 Announce Type: replace-cross Abstract: Translating single-cell RNA sequencing (scRNA-seq) data into mechanistic biological hypotheses remains a critical bottleneck, as agentic AI sy

arXiv:2607.29058v1 Announce Type: new Abstract: Professional-document review is a constraint-checking problem in which decisions depend on relations among text, geometry, pages, and document revisions

arXiv:2607.29087v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed in enterprise settings, yet individual models remain bounded by model-specific capability limitat

Hey, Like a lot of people here, I use local models via Ollama on my desktop/server and wanted a mobile client that actually felt responsive, worked offline, and respected privacy. Most apps on the Pla

arXiv:2607.29274v1 Announce Type: cross Abstract: Claims that language models homogenise are usually measured against human judgements collected for the study, which makes the human side an artifact o

arXiv:2607.28669v1 Announce Type: new Abstract: We present LARA (Lightweight Additive Residual Adaptation), a method for efficient adaptation that operates in the residual stream of a frozen model rat

arXiv:2607.29039v1 Announce Type: new Abstract: Multimodal medical anomaly detection identifies samples deviating from normal patterns, where scarce abnormal cases make normality modeling from normal

arXiv:2607.28969v1 Announce Type: new Abstract: Although Large Language Models (LLMs) have demonstrated promising safety performance, extending them to Multimodal Large Language Models (MLLMs) exposes

arXiv:2607.29367v1 Announce Type: new Abstract: Satellite image editing requires spatially precise object-level control, but supervised editing datasets for overhead imagery are costly to build becaus

arXiv:2607.29363v1 Announce Type: cross Abstract: Balancing sequence length, representational capacity, and long-horizon stability is a central problem in autoregressive (AR) speech and audio generati

arXiv:2607.28633v1 Announce Type: cross Abstract: Disaggregated LLM inference creates a datacenter networking problem that no existing system solves correctly. When prefill and decode run on separate

arXiv:2607.29496v1 Announce Type: new Abstract: We study transcript management for fixed, finite-precision causal Transformers. A transcript is partitioned into channels of bounded blocks. Each transi

arXiv:2607.29617v1 Announce Type: cross Abstract: Imitation learning (IL)---training an agent to replicate expert behavior from demonstrations---underpins applications from robotics to language model

You shouldn't need a vision model to know your PDF has checkboxes. LiteParse can now pull structured data directly from your PDFs: form field values, checkbox states, annotations, embedded images, vec

Hey all, tldr / who this helps: you run a mixed multi-GPU box where the experts spill to RAM, and you want to stay in the 3-bit tier instead of dropping to Q2 to make it fit. https://huggingface.co/Ta

I deployed K3 on 32 H100s at work a couple of weeks ago and then got annoyed that there was no way to poke at it on my own machine. So I wrote an inference engine for it in C99. Nothing clever going o

TL;DR: I spent 9 days developing a new quantization method for MLX models and measured 18 variants against each other on a single M5 Max MacBook Pro (128 GB). The result is the best-measuring MLX quan

2/ a cost benchmark showed the same coding task running three to four times cheaper, depending purely on the harness wrapped around the model. Same intelligence, wildly different accuracy and cost, de