Search: “llm”

For example, directly using claude code or code, which is then hooked up to automatically delegate the actual code writing tasks to a local model like qwen 3.8 flash next, to save on cloud usage limit

arXiv:2609.34861v1 Announce Type: new Abstract: Visual token pruning has been widely studied as a practical approach to reducing the computational cost of large vision-language models. However, it str

arXiv:2609.34554v1 Announce Type: new Abstract: Memory is essential for long-horizon, partially observed robotic manipulation: a robot must remember which object was placed in a drawer, whose cup it m

arXiv:2609.34065v1 Announce Type: cross Abstract: Names are personal identifiers, but they also carry social meaning and are widely used to evaluate how language models treat different people. Such ev

arXiv:2609.30813v1 Announce Type: new Abstract: Evaluating claim admission in shared agent memory is challenging because repeated claims may be mistaken for independent evidence. An agent may copy or

arXiv:2609.30631v1 Announce Type: cross Abstract: Online audio-visual target-speaker extraction aims to remove competing voices while preserving speech quality and bounding lookahead. Existing extract

arXiv:2609.31260v1 Announce Type: cross Abstract: We investigate the systemic macroscopic dynamics emerging from Limit Order Books (LOBs) populated exclusively by autonomous reinforcement-learning age

arXiv:2609.30725v1 Announce Type: new Abstract: Although effective, coding agents often incur substantial monetary costs. Their recurring cost-inefficient behaviors remain underexplored. We conduct th

arXiv:2609.30541v1 Announce Type: new Abstract: Optimizing embedding systems for production recommendation pipelines demands systematic exploration that consumes disproportionate engineering effort at

context : do not re-reserve the scheduler when toggling causal_attn (#28751) context : do not re-reserve the scheduler when toggling causal_attn llama_context::set_causal_attn() marks the scheduler to

arXiv:2602.02043v2 Announce Type: replace-cross Abstract: Modern vision-language models struggle with basic compositional reasoning, failing to bind attributes to objects or relations to their referen

arXiv:2609.30489v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated historic breakthroughs in general reasoning with early successes in biomedical science. However, existing

arXiv:2609.30293v1 Announce Type: cross Abstract: The Model Context Protocol (MCP) enables AI agents to discover and call tools, but loading every definition becomes expensive as connected catalogs gr

Claude Sonnet 5.5 New Sonnet model from Anthropic today. They say it 'runs 30%+ faster, and costs up to 30% less for most work' - it's priced the same as Sonnet 5 but appears to beat it on every bench

arXiv:2609.30345v1 Announce Type: cross Abstract: Cloud-security investigation is dominated by population tasks: which identities can read a data store, how many resources fail a control, which assets

arXiv:2609.31272v1 Announce Type: cross Abstract: AI is becoming increasingly integrated into daily workflows, especially in computing. We are gradually shifting towards an AI-rich future, an impendin

arXiv:2609.31381v1 Announce Type: new Abstract: Context projection replaces older tool observations with compact, addressable excerpts, reducing repeated input while potentially adding evidence-retrie

arXiv:2609.30974v1 Announce Type: new Abstract: Lexical semantic change is usually summarized by a scalar distance between independently sampled period distributions. This measures how much a word cha

arXiv:2609.31103v1 Announce Type: cross Abstract: Spatial reasoning with metric constraints requires linking objects to geometric measurements and preserving their numerical content during language re

arXiv:2609.30977v1 Announce Type: cross Abstract: Uniform discrete diffusion models (UDMs) commonly use explicit time conditioning, but we find that it can often be unnecessary in practice. In this pa

arXiv:2609.30611v1 Announce Type: cross Abstract: On Jan. 30, 2026, the U.S. Department of Justice released a mixed-media collection concerning Jeffrey Epstein, including about three million pages of

arXiv:2609.30535v1 Announce Type: new Abstract: Children in multilingual communities often code-switch, using multiple languages in a single utterance. Can we induce cross-lingual alignment in languag

arXiv:2602.09163v2 Announce Type: replace Abstract: Scientific knowledge bases accelerate discovery by curating findings from primary literature into structured, queryable formats for both human resea

arXiv:2609.31450v1 Announce Type: cross Abstract: Medical vision-language model (VLM) post-training is commonly evaluated through answer accuracy. We examine how changes in accuracy and training objec

arXiv:2609.31595v1 Announce Type: new Abstract: 3D scene graphs provide a structured representation of complex environments by encoding objects, their semantic attributes, and the spatial and function

arXiv:2609.30326v1 Announce Type: new Abstract: Activation steering changes a model's internal activations during inference without updating its weights, but a useful intervention must determine both

Introducing FireRouter with Opus. Our first router model. Routine tasks go to top open models, Claude Opus handles the rest. Cache and task-aware routing. Proven 98.1% of Opus accuracy with 57% lower

arXiv:2609.30706v1 Announce Type: new Abstract: 'System One' decision models such as TypeSafe's Jev and its open counterpart Laya answer typed questions about a text in a single forward pass with cali

arXiv:2609.30943v1 Announce Type: new Abstract: Long-form technical text generation underpins knowledge-intensive workflows, yet remains challenging for large language models (LLMs) due to the need fo

arXiv:2609.30288v1 Announce Type: new Abstract: In Transformer-based masked language models, attention is the primary mechanism for context mixing, but there are other ways to mix data across tokens.

arXiv:2609.31285v1 Announce Type: new Abstract: Facial micro-expressions are spontaneous, brief, and subtle facial movements that reveal suppressed emotions in high-stakes environments. In contrast to

arXiv:2609.30609v1 Announce Type: new Abstract: Multi-shot agentic video generation requires consistent character appearance, stable spatial layout across camera angles, and continuous character state

arXiv:2609.31255v1 Announce Type: new Abstract: General-purpose agent memory summarizes conversations: it extracts salient snippets, embeds them, and retrieves the top-k into the prompt. A health agen

arXiv:2609.30657v1 Announce Type: cross Abstract: Large language model email assistants are particularly vulnerable to indirect prompt injection because untrusted email content can be retrieved into t

arXiv:2609.31505v1 Announce Type: new Abstract: Despite the growing capabilities of large language models (LLMs), prompt design remains largely heuristic and ad hoc. This project will explore extit{pr

arXiv:2609.30578v1 Announce Type: new Abstract: Language models gain accuracy from more compute at test time, but majority voting over independent samples saturates: as samples grow, the vote converge

arXiv:2609.30918v1 Announce Type: cross Abstract: Robust counterfactual explanations promise recourse that still works after the model behind it changes. Whether they keep that promise depends on what

arXiv:2609.30295v1 Announce Type: cross Abstract: Identifying an unfamiliar sign is difficult when a learner remembers its movement but does not know its meaning or formal feature codes. SignTrace add

arXiv:2609.31607v1 Announce Type: cross Abstract: Generative AI systems are increasingly used, but aligning their outputs with user requirements poses a continuing challenge. Here, we aim to ensure th

arXiv:2609.30383v1 Announce Type: new Abstract: A skill is a modular package of natural-language instructions, executable scripts, and reference resources that an agent can load at runtime to extend i

arXiv:2605.06642v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly used as interactive agents, but optimizing them for long-horizon decision making remains difficu

arXiv:2609.31524v1 Announce Type: new Abstract: Surgical scene understanding is critical for computer-assisted intervention, yet laparoscopic cholecystectomy remains challenged by the complex anatomy

The OpenAI-Hugging Face hack was enabled by weak sandboxing. It is great that Nvidia is releasing open source tools for sandboxing AI agents. OpenWorker, our open-source agent harness supporting cyber

arXiv:2609.31422v1 Announce Type: cross Abstract: Large language model-based multi-agent debate (MAD) systems are being increasingly used as complex decision pipelines in distributed processes. Howeve

arXiv:2609.30670v1 Announce Type: new Abstract: Streaming video understanding requires models to interpret evidence as it arrives, yet current evaluations often report task scores without specifying w

TL;DR: The Jeff models are a set of Qwen3.5 and Gemma fine-tunes for zero-shot classification: small, efficient, open-weight models with respectable out-of-the-box performance that can be slotted righ