All entries

LEGO Co-builder: Exploring Fine-Grained Vision-Language Modeling for Multimodal LEGO Assembly Assistants

arXiv:2507.05515v4 Announce Type: replace Abstract: Vision-language models (VLMs) are facing the challenges of understanding and following multimodal assembly instructions, particularly when fine-grai

Local Ai

Let AI Agents Translate Networks, Not Reason About Them

DGX agent

arXiv:2607.22947v1 Announce Type: new Abstract: A formal model enables verifying reachability, localizing an outage, or anticipating the blast radius of a change. Yet, virtually no production network

local-aiarxiv-cs-ai

28 Jul 2026

Let Me Look at You: Advanced Facial Expression Modeling for Conversational Speech Synthesis

arXiv:2607.24430v1 Announce Type: cross Abstract: Conversational Speech Synthesis is a fundamental component of human-computer interaction, aiming to generate contextually appropriate, expressive, and

applicationsarxiv-cs-cl

LEX-EC: A Lexical Evidence-Channel Audit Framework for Zero-Shot LLM Personality Classification in Black-Box Settings

arXiv:2607.24435v1 Announce Type: cross Abstract: Large language models may easily assign personality labels from text, but model interpretability remains an open problem. To address this gap, we intr

researcharxiv-cs-ai

Lexical discovery in unknown environments orchestrated by Large Language Models

arXiv:2607.22591v1 Announce Type: new Abstract: Populations of autonomous agents deployed in unknown environments (e.g. planetary or deep-sea exploration) must develop shared vocabularies to refer to

agentsarxiv-cs-ai

LFM2.5-Encoders: Fast at Long Context, Even on CPU

model-releasesr-localllama

LFM2.5-Encoder is a family of multilingual bidirectional encoders built on the LFM2 architecture, available in two sizes: LFM2.5-Encoder-230M — a lightweight encoder for tight latency and memory budge

LIBMoE: A Library for comprehensive benchmarking Mixture of Experts in Large Language Models

arXiv:2411.00918v5 Announce Type: replace-cross Abstract: Mixture of experts (MoE) architectures have become a cornerstone for scaling up and are a key component in most large language models such as

Like a Baby: Visually Situated Neural Language Acquisition

arXiv:1805.11546v3 Announce Type: replace-cross Abstract: We examine the benefits of visual context in training neural language models to perform next-word prediction. A multi-modal neural architectur

tutorialsarxiv-cs-ai

Like a bilingual baby: The advantage of visually grounding a bilingual language model

arXiv:2210.05487v3 Announce Type: replace Abstract: Unlike most neural language models, humans learn language in a rich, multi-sensory and, often, multi-lingual environment. Current language models ty

tutorialsarxiv-cs-cl

Limbomorphs

arXiv:2607.23842v1 Announce Type: cross Abstract: Artificial life systems are typically defined by a set of dynamical rules over an environment, an agent, or both, from which lifelike patterns may eme

agentsarxiv-cs-ai

LithoFormer: A Robust Framework for Stratigraphic Inference via Transformers

arXiv:2607.22804v1 Announce Type: cross Abstract: Accurate geological characterization of subsurface reservoirs from well log data is essential to support projects such as carbon capture and storage (

applicationsarxiv-cs-ai

LLM-Assisted Ontology Engineering and Construction of a French Legal Knowledge Graph

arXiv:2607.24551v1 Announce Type: new Abstract: Maintenance regulations are complex legal texts that are difficult to exploit when addressing a specific case and challenging to integrate into operatio

LLM-Based Scientific Equation Discovery via Physics-Informed Token-Regularized Policy Optimization

arXiv:2602.10576v2 Announce Type: replace-cross Abstract: Symbolic regression aims to distill mathematical equations from observational data. Recent approaches have successfully leveraged Large Langua

LLM-based Source Code Compression via Thresholded Symbol Ranking

arXiv:2607.24192v1 Announce Type: cross Abstract: We study the problem of lossless compression of source code, motivated by the storage demands of large-scale software archives, such as Software Herit

researcharxiv-cs-cl

LLM-Based vs. Lexicon-Based Sentiment Signals for Tail-Risk Detection in Meme Stocks

arXiv:2607.24072v1 Announce Type: new Abstract: This paper presents an empirical comparison of lexicon-based and Large Language Model (LLM)-based sentiment analysis for extracting market-relevant sign

researcharxiv-cs-cl

LLM-SoccerArena: Benchmarking LLMs on Real-World Predictions in Sports

arXiv:2607.24573v1 Announce Type: new Abstract: Large language models (LLMs) increasingly support decisions about uncertain future events, yet evaluating their ability to forecast real-world outcomes

Local Regularization Does Not Characterize Multiclass PAC Learnability

arXiv:2607.23449v1 Announce Type: new Abstract: Local regularization assigns each hypothesis a test-point-dependent score and predicts with a minimum-score hypothesis consistent with the sample. Asili

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding

arXiv:2607.24555v1 Announce Type: cross Abstract: Serving large language models at long context is bottlenecked by the key-value (KV) cache, which is read in full at every decode step. Attention keys

local-aiarxiv-cs-ai

LOCUS: Local Visual Cue Search for Enhancing Fine-Grained Perception in Multimodal Large Language Models

arXiv:2606.16586v2 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) remain unreliable on fine-grained visual perception, even when high-resolution inputs preserve the necessar

local-aiarxiv-cs-cv

Logit-Coordinate Generative Models for Mixed Continuous-Categorical Tabular Data

arXiv:2607.23348v1 Announce Type: cross Abstract: Mixed continuous--categorical data pose a representation problem for continuous generative models. Flow Matching and Gaussian diffusion operate in Euc

Long-Tailed Medical Image Classification

arXiv:2607.23883v1 Announce Type: new Abstract: In this paper, we examine the difficulties of using standard techniques for medical image classification due to long-tailed distributions (wherein rarer

safetyarxiv-cs-cv

LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget

arXiv:2607.14952v3 Announce Type: replace Abstract: Long-context RL post-training is constrained by the lifetime of state and gradients, not attention cost alone. In GRPO, one multi-million-token prom

safetyarxiv-cs-lg

Looking for Affect in Spontaneous Finnish Speech through Linguistic Interpretability

model-releasesarxiv-cs-cl

arXiv:2607.24155v1 Announce Type: new Abstract: Existing research on affect in speech has shown how acoustic surface characteristics and content-related linguistic aspects of speech both relate to per

Loong: Synthesize Long Chain-of-Thoughts at Scale through Verifiers

arXiv:2509.03059v2 Announce Type: replace-cross Abstract: Recent advances in Large Language Models (LLMs) have shown that their reasoning capabilities can be significantly improved through Reinforceme

Looping Is Not Reliability: State-Bound Evidence and Typed Revision Contracts for Agentic Code Repair

arXiv:2607.24604v1 Announce Type: cross Abstract: Generate--test--revise loops are common in coding agents, but repetition alone provides no reliability guarantee. We study the gap between finding a c

LoRA for Gender-Inclusive Rewriting and Activation Steering for Counter-Narrative Generation

model-releasesarxiv-cs-cl

arXiv:2607.23083v1 Announce Type: new Abstract: Gender-inclusive language generation seeks to transform biased text into inclusive alternatives while preserving semantic meaning and contextual coheren

LoRA over GGUF: Train DeepSeek-V4-Flash in 90G VRAM

model-releasesr-localllama

https://github.com/woct0rdho/transformers5-qwen3.5-recipe An update on my progress with low-VRAM LoRA training over GGUF base model: Now we can train DeepSeek-V4-Flash (284B-A13B) in 90 GiB VRAM, with

Loss-Aware Feature-Map Pruning in Convolutional Neural Networks Using Multi-Armed Bandits

arXiv:2607.22564v1 Announce Type: new Abstract: Convolutional neural networks often contain redundant feature maps that increase storage and inference cost. This paper presents a loss-aware feature-ma

researcharxiv-cs-ai

LoTA-N2N: Local Trace Adaptation for Zero-Shot Self-Supervised Image Denoising

model-releasesarxiv-cs-cv

arXiv:2607.24135v1 Announce Type: new Abstract: Single-image self-supervised denoising replaces unavailable clean targets with surrogate targets constructed from noisy observations. Its effectiveness

Low-Latency Turn-Taking via Context-Aware Preface Generation in a Real-World Dialogue Robot

arXiv:2607.23204v1 Announce Type: cross Abstract: Large language model (LLM)-based dialogue systems suffer response delays because generation begins only after final speech recognition. While fixed fi

applicationsarxiv-cs-cl

Low-light Image Enhancement via Multi-scale Attention combined with Fourier Transform

arXiv:2607.24002v1 Announce Type: new Abstract: Low-light image enhancement (LLIE) aims to improve image quality and clarity in diverse and demanding low-illumination environments. However, existing d

applicationsarxiv-cs-cv

Low-Rank Dependence Decomposition via Accelerated Symmetric Non-negative Matrix Factorization

model-releasesarxiv-cs-lg

arXiv:2607.24518v1 Announce Type: new Abstract: Symmetric non-negative matrix factorization (SymNMF) recovers latent group structure from a dependence matrix, but its dense, quadratic-memory objective

LowAux-RDNet: Low-Pass Residual Supervision with Scene-Balanced Real-World Training for Single-Image Reflection Removal

model-releasesarxiv-cs-cv

arXiv:2607.22707v1 Announce Type: new Abstract: Single-image reflection removal aims to recover a clean transmission layer from one image captured through glass. We study an explicit decomposition pip

LU-500: A Logo Benchmark for Concept Unlearning

arXiv:2607.24101v1 Announce Type: cross Abstract: Concept unlearning is increasingly used to limit the reproduction of protected or unsafe visual concepts in text-to-image models. Existing evaluations

LuxInstruct: A Cross-Lingual Instruction Tuning Dataset For Luxembourgish

arXiv:2510.07074v2 Announce Type: replace-cross Abstract: Instruction tuning has become a key technique for enhancing the performance of large language models, enabling them to better follow human pro

Machine Learning for Cloud Detection in IASI Measurements: A Data-Driven SVM Approach with Physical Constraints

arXiv:2508.10120v2 Announce Type: replace-cross Abstract: Cloud detection is fundamental for the interpretation and operational exploitation of hyperspectral infrared sounders, yet the capability of i

Making Mathematical Knowledge Explainable, Accessible and Interoperable Through Large Language Model Integration

arXiv:2607.24512v1 Announce Type: new Abstract: Mathematical models are central to formalizing research problems, yet their documentation often falls short of FAIR principles. Knowledge bases such as

Mamba-CL: Optimizing Selective State Space Model in Null Space for Continual Learning

arXiv:2411.15469v3 Announce Type: replace Abstract: Continual Learning (CL) aims to equip AI models with the ability to learn a sequence of tasks over time, without forgetting previously learned knowl

tutorialsarxiv-cs-cv

Manga Coloring Tool 2

local-air-stablediffusion

Hey everyone! 👋 I'm excited to announce the official release of Manga Coloring Tool 2.0, a completely free, local, open-source web application designed to colorize manga pages and chapters effortlessl

MANGO: A Global Single-Date Paired Dataset for Mangrove Segmentation

arXiv:2601.17039v2 Announce Type: replace-cross Abstract: Mangroves are critical for climate-change mitigation, requiring reliable monitoring for effective conservation. While deep learning has emerge

Manifold-Constrained Noise Optimization for Diverse Diffusion Sampling

arXiv:2607.23937v1 Announce Type: new Abstract: Few-step distilled diffusion models generate high-quality images quickly, but often lose per-prompt diversity, producing near-identical samples across r

researcharxiv-cs-cv

Tools

Many AI tools rent intelligence. Kimi K3 on Fireworks is different. Fine-tune it on your own data, serve from US-hosted endpoints, and own t…

Many AI tools rent intelligence. Kimi K3 on Fireworks is different. Fine-tune it on your own data, serve from US-hosted endpoints, and own the weights. Zero data retention. ICYMI yesterday, start buil

toolsfireworks-ai--x

MAPLE: Efficient and Diverse Multi-Alpha Generation for Portfolio Construction

arXiv:2607.24131v1 Announce Type: new Abstract: Classical alpha mining achieves strong risk-adjusted returns by combining many low-correlated predictive signals, yet deep learning stock-ranking method

MarineEVT: Advancing Event-Centric Marine Video Understanding via Visual Tool Reasoning

arXiv:2607.24064v1 Announce Type: cross Abstract: Recent Vision-Language Models (VLMs) have achieved remarkable success in visual understanding, driven by the growing availability of high-quality imag

local-aiarxiv-cs-ai

Markerless Motion Capture in Routine Clinical Upper Limb Assessments: Validity and Insights Beyond Ordinal Scoring

arXiv:2607.23608v1 Announce Type: new Abstract: The Action Research Arm Test (ARAT) is a widely-used upper limb outcome measure in neurorehabilitation, but its ordinal scoring is subjective and suffer

researcharxiv-cs-cv

Market surveillance agent with LangGraph and Strands on AgentCore

Learn how to architect and deploy a production-ready multi-agent AI system using LangGraph for workflow orchestration and Strands for agent reasoning on Amazon Bedrock AgentCore. This post walks throu

agentsaws-ml-blog

MARS: Multi-hop Adaptive Retrieval and SPARQL Generation for KGQA

arXiv:2607.14561v2 Announce Type: replace Abstract: Large language models (LLMs) have demonstrated strong reasoning performance, but their tendency to hallucinate limits their reliability in knowledge

agentsarxiv-cs-cl

Masked Autoencoders Learn Perception-Relevant Representations from Resting State Neural Data

arXiv:2607.22615v1 Announce Type: cross Abstract: Clinical neuroprosthetics face a data bottleneck: labeled perception trials are scarce while hours of spontaneous neural activity are largely underuti

tutorialsarxiv-cs-ai