All entries

arXiv:2608.07648v1 Announce Type: cross Abstract: Sampling high-dimensional probability distributions is a central task in scientific computing, with applications ranging from Bayesian inference to st

tutorialsarxiv-cs-lg

Leveraging the frontier ecosystem We work with neolabs like @trajectorylabs and @EngramLab and inference + post-training infra providers lik…

DGX agent

Leveraging the frontier ecosystem We work with neolabs like @trajectorylabs and @EngramLab and inference + post-training infra providers like @baseten, @FireworksAI_HQ, and @appliedcompute to post-tra

applicationsfireworks-ai--x

11 Aug 2026

LexKairos: Benchmarking Legal Temporal Capabilities in LLMs

model-releasesarxiv-cs-cl

arXiv:2608.09106v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated strong performance across a wide range of legal tasks. In legal practice, time is a critical concept that

LF{}^{2}AR: Accounting for Layerwise Dynamics to Improve Multimodal Adaptation of Language Models

arXiv:2503.06211v3 Announce Type: replace-cross Abstract: Text-pretrained language models (LMs) encode rich world knowledge, but adapting them to process and generate perceptual modalities such as aud

safetyarxiv-cs-ai

LGNNIC: Acceleration of Large-Scale GNN Training using SmartNICs

arXiv:2608.07733v1 Announce Type: cross Abstract: Graph Neural Networks (GNNs) are widely used across domains such as natural sciences, social network analysis, chip design, and recommendation systems

LHSDet: High-Resolution AI-Generated Image Detection via Visual Question Answering

arXiv:2608.07863v1 Announce Type: new Abstract: Driven by advances in diffusion models and autoregressive models, the fidelity and resolution of AI-generated images now rival those of real images. How

LIBAD: A Multimodal Anomaly Detection Benchmark for Li-Ion Battery Electrode Manufacturing

model-releasesarxiv-cs-cv

arXiv:2608.07958v1 Announce Type: new Abstract: Multimodal industrial anomaly detection has largely focused on discrete products using strongly correlated RGB and 3D observations, leaving continuous p

LibraSpec: Dynamic Diffusion-Based Speculative Decoding via Marginal-Gain-Driven Optimization

arXiv:2608.08721v1 Announce Type: cross Abstract: Speculative decoding accelerates large language model inference by drafting multiple tokens for parallel verification, with efficiency critically dete

LightAIR: Lightweight Action Inversion and Riemannian Rectification for Text-based Person Anomaly Search

arXiv:2608.09152v1 Announce Type: new Abstract: Traditional Text-based Person Search (TPS) is typically limited to matching static appearance attributes, severely neglecting dynamic action information

Linearized 2-Simplicial Attention

arXiv:2608.09307v1 Announce Type: new Abstract: We present a linearized form of 2-simplicial attention by rewriting the trilinear score as an inner product between a composite query and a key, so that

Applications

LineGraph2Road: Structural Graph Reasoning on Line Graphs for Road Network Extraction

arXiv:2602.23290v2 Announce Type: replace Abstract: Extracting routable road networks from satellite imagery requires accurate topology recovery beyond pixel-level segmentation. Recent methods decompo

applicationsarxiv-cs-cv

Agents

Lingjing: A Simulation Testbed for Multi-Agent Embodied Tasks in Open-Ended Cities

arXiv:2608.08045v1 Announce Type: new Abstract: Urban embodied intelligence requires coordination among heterogeneous agents (e.g., UAVs, ground robots, and autonomous vehicles) in dynamic cities. Sim

agentsarxiv-cs-ai

Linguistically-Aligned and Visually-Grounded Preference Optimization for Clinically-Augmented Medical Report Generation

arXiv:2608.08494v1 Announce Type: new Abstract: Despite significant advances in Medical Report Generation (MRG), the reliability remains constrained by the prevalence of factual errors. While Direct P

safetyarxiv-cs-cv

LIRA: Local Cross-Layer Information Routing for Vision-Language-Action Decoding

model-releasesarxiv-cs-cv

arXiv:2608.07596v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models transform representations from pretrained vision-language models (VLMs) into robot actions, yet the interface that

Listen, See and Track: Spatio-Temporal Audio-Visual Sound Event Reasoning for Omni-Modal Language Models

arXiv:2608.09435v1 Announce Type: new Abstract: Understanding dynamic sound sources requires jointly determining what produces a sound, where the source is located, and how it moves over time. Yet exi

Listwise Cross-Encoder Fine-Tuning vs. Agentic Instruction Tuning for LLM Rerankers: A Systematic Study in Medical Procedure Reranking

model-releasesarxiv-cs-cl

arXiv:2608.09650v1 Announce Type: cross Abstract: Reranking medical procedures against patient queries is a critical component of health insurance information retrieval, complicated by a substantial l

LITEWAY: LIghtweight HAR via Temporal Efficient highWAY

arXiv:2608.09421v1 Announce Type: cross Abstract: Wearable human activity recognition (HAR) remains challenging due to the computational and energy constraints of deep learning models on resource-limi

Llama-CPP Parallel Agents --> fine for decode, but one agent's prefill will grind all other agents to a halt

Testing with 3-5 agents. Decode performance is superb, however if one performs a web search and needs to process a few thousand tokens, ALL other agents will grind to a halt: I've tried tuning a littl

[llama.cpp PR #26608] Ling-3.0 support (unmerged)

aetherbird has done some great work getting Ling-3.0 to work in llama.cpp. The architecture is generally identical to deepseekv2. I recently added a microscopic 40 line PR to his that adds support for

LLM-Based Embeddings for Program Analysis and Optimization

arXiv:2608.07894v1 Announce Type: new Abstract: Recent advances have highlighted the potential of machine learning, particularly Large Language Models (LLMs), for analyzing and optimizing programs. We

LLM-Driven AutoML for Cross-Lingual Handwritten OCR: Closed-Loop Neural Architecture Search with GPT-5, GPT-4o, and Claude Sonnet 4

arXiv:2607.15509v2 Announce Type: replace-cross Abstract: We present a fully automated closed-loop AutoML framework that uses GPT-5, GPT-4o, and Claude Sonnet 4 as autonomous neural architecture desig

LLM-Guided Heuristic Design from Simulation Traces: A Case Study in Dynamic Production and AGV Scheduling

arXiv:2608.09343v1 Announce Type: new Abstract: Simulation-based optimization (SBO) evaluates executable policies under stochastic dynamics, but most methods treat the simulator as a black box: aggreg

LLM Reasoning for Subjective Tasks: Failure Modes, Mitigation, and Dynamic Reasoning Routing

arXiv:2608.08889v1 Announce Type: new Abstract: Recommendation systems thrive on personalization, where ''correctness'' is rarely a binary truth but a matter of subjective human preference. As Large L

safetyarxiv-cs-ai

LLM within MCP Matters: Measuring Inefficient Resource Utilization Driven by LLMs

arXiv:2608.08467v1 Announce Type: new Abstract: The Model Context Protocol (MCP) standardizes how servers expose data and tools to Large Language Models (LLMs). A common server design embeds frequentl

LLMs Remember First, Forget Last: Dual-Process Interference in Large Language Models

arXiv:2603.00270v3 Announce Type: replace-cross Abstract: Large language models can process millions of tokens, yet how they handle conflicting information within context remains poorly understood. Fr

safetyarxiv-cs-ai

LLMs still produce bugs, but those bugs are different than what they used to be. It’s less off-by-ones and more about system design, ui usab…

model-releasesboris-cherny--x

LLMs still produce bugs, but those bugs are different than what they used to be. It’s less off-by-ones and more about system design, ui usability, missing broader context. Some kinds of coding has bee

LLMVisor: A Real-Time Latency Attribution Model for Multi-Tenant LLM Serving

arXiv:2608.08382v1 Announce Type: new Abstract: As LLM inference shifts to multi-tenant GPU clusters, co-batching improves throughput but obscures per-tenant usage and limits control. Enabling fractio

Local Benchmark : Muse Glimmer 30B vs Qwen 3.6 27B vs Gemma4 31B (and many other models and finetunes)

Needs a lot of requests compared to Qwen (almost twice) and Gemma (almost x3). Final score is fine, even though it is 'not a coding model' https://wonderrico.github.io/local_llm_benchmark/benchmark-ma

Locating Failure in Multi-Page Visually Rich Document Understanding: An Empirical Attribution

arXiv:2608.07943v1 Announce Type: new Abstract: Multi-page visually-rich document understanding (MP-VRDU) requires managing evidence that is sparse, spread across pages, and often exceeds a model's co

Logarithmic-Free Moment and Generalization Bounds for Uniformly Stable Algorithms

arXiv:2608.09870v1 Announce Type: cross Abstract: Uniform stability is a classical tool for controlling the generalization error of a learning algorithm. Bousquet, Klochkov, and Zhivotovskiy (2020) sh

LogicIF: Towards Complex Logic Instruction Following

model-releasesarxiv-cs-cl

arXiv:2508.09125v4 Announce Type: replace Abstract: Instruction following has catalyzed the recent era of Large Language Models (LLMs) and is the foundational skill underpinning more advanced capabili

LogiShot: Logically Coherent Cross-Shot Video Generation

model-releasesarxiv-cs-cv

arXiv:2608.08820v1 Announce Type: new Abstract: Generating cross-shot videos that are logically connected is essential for content creation. Currently, most cross-shot video-generation workflows, such

Long SKILL Compliance as Logical Reasoning: Closure-Grounded Detection with Scaling-Guided On-Policy Distillation

arXiv:2608.08146v1 Announce Type: new Abstract: The increasing complexity of enterprise business scenarios has promoted the widespread adoption of long SKILL documents in agent systems, posing new cha

LookAgain: Closed-Loop GUI Grounding with Visually Grounded Reflection

arXiv:2608.09723v1 Announce Type: new Abstract: Recent graphical user interface (GUI) grounders have significantly advanced single-shot accuracy on standard benchmarks, yet their performance degrades

Looker’s semantic layer governs Gemini Enterprise data for user trust

model-releasesgoogle-cloud-ai

For organizations deploying AI agents at scale, there’s often a critical divide between structured and unstructured data. While large language models (LLMs) excel at parsing text documents, emails, an

Looking for a faster specialized model for your Agent Work? @nvidia Nemotron 3.5 Lightning (30B MoE, 3B active params) is now live on Firewo…

model-releasesfireworks-ai--x

Looking for a faster specialized model for your Agent Work? @nvidia Nemotron 3.5 Lightning (30B MoE, 3B active params) is now live on Fireworks. It’s distilled from NVIDIA Nemotron 3 Ultra to be your

LookME: Lookup-Based Multimodal Embeddings for Layer Injection in Vision-Language Models

arXiv:2607.16305v2 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) have achieved strong progress in multimodal understanding. However, scaling dense or sparse Mixture-of-Experts (

LoRA-based Adaptation Alone Is Not Enough: Understanding the Limits of Foundation Models for Face Presentation Attack Detection

arXiv:2608.09633v1 Announce Type: new Abstract: Face presentation attack detection (PAD) aims to reliably detect a wide range of presentation attacks. While PAD methods achieve strong performance with

LoRSA: Toward Generalizable Parameter-Efficient Fine-Tuning for Biomedical Downstream Tasks

arXiv:2608.07749v1 Announce Type: cross Abstract: Parameter-efficient fine-tuning enables the adaptation of vision foundation models to biomedical tasks under limited computational resources, but a si

Loss-Resilient Wireless Video Token Communication over Block Fading Channels

arXiv:2608.08698v1 Announce Type: new Abstract: Video token communication represents video content as discrete tokens that differ in their importance to reconstruction and exhibit temporal dependencie

LUCID: Latent-Skill Unified Control via Imagined Dynamics for Long-Horizon Humanoid Loco-Manipulation

arXiv:2608.07746v1 Announce Type: new Abstract: Long-horizon humanoid loco-manipulation requires composing versatile whole-body skills and reliable high-level decision making. Existing methods often c

safetyarxiv-cs-lg

Luth-2: New State-of-the-Art French Small Language Models

Hey everyone, Today we release Luth-2-0.8B and Luth2-2-2B, two non-reasoning models that set a new state of the art for French across a wide variety of tasks for their size 🚀 A few notable scores on F

Lying mirror using structured surfaces

arXiv:2410.15521v2 Announce Type: replace-cross Abstract: We introduce an all-optical system, termed the 'lying mirror', to hide input information by transforming it into misleading, ordinary-looking

Agents

M^3Prune: Hierarchical Communication Graph Pruning for Efficient Multi-Modal Multi-Agent Retrieval-Augmented Generation

arXiv:2511.19969v2 Announce Type: replace Abstract: Recent advancements in multi-modal retrieval-augmented generation (mRAG), which enhance multi-modal large language models (MLLMs) with external know

agentsarxiv-cs-ai

Local Ai

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA

arXiv:2608.09819v1 Announce Type: cross Abstract: Macaron-V1 is an open agent-model family for experiential intelligence: learning from experience in real environments and continuing to learn after de

local-aiarxiv-cs-cl

Machine Learning and Data Analysis Using Posets: A Survey

arXiv:2404.03082v3 Announce Type: replace Abstract: Partially ordered sets (posets) are discrete mathematical structures that formalize the notion of comparison without forcing every pair of objects t

safetyarxiv-cs-lg

Machine-Learning-Based Diagnostic Framework for Passive Ultrasonic Detection of Railway Wheel Defects

arXiv:2608.08301v1 Announce Type: new Abstract: Reliable identification of railway wheel defects is important for safety and maintenance. This study develops a machine-learning-based diagnostic framew

safetyarxiv-cs-lg

Machine Learning for Inverse Problems and Data Assimilation

arXiv:2410.10523v3 Announce Type: replace-cross Abstract: The aim of this book is to demonstrate the potential for ideas in machine learning to impact on the fields of inverse problems and data assimi