local ai

R-APS: Compositional Reasoning and In-Context Meta-Learning for Constrained Design via Reflective Adversarial Pareto Search

arXiv:2606.04823v1 Announce Type: new Abstract: Large language models (LLMs) are fluent on open-ended tasks, yet in agentic settings, where a system must plan, use tools, and act over extended horizon

Local Ai

Reasoning or Fluency? Dissecting Probabilistic Confidence in Best-of-N Selection

DGX agent

arXiv:2601.13735v2 Announce Type: replace Abstract: Probabilistic confidence metrics are increasingly adopted as proxies for reasoning quality in Best-of-N selection, under the assumption that higher

local-aiarxiv-cs-ai

4 Jun 2026

Recover-LoRA for Aggressive Quantization: Reclaiming Accuracy in 2-Bit Language Models via Low-Rank Adaptation with Knowledge Distillation on Synthetic Data

arXiv:2606.04238v1 Announce Type: cross Abstract: Aggressive weight quantization to 2-bit precision offers substantial throughput and memory gains for large language model (LLM) inference, but typical

RowNet: A Memory Transformer for Tabular Regression

arXiv:2606.04445v1 Announce Type: cross Abstract: Real estate valuation is a structured regression problem in which prices are governed by heterogeneous feature types, sparse regional effects, nonline

SBP-Net: Learning Thin Structure Reconstruction with Sliding-Box Projections

arXiv:2606.04251v1 Announce Type: new Abstract: Reconstructing thin 3D structures is challenging due to their sparsity, scale variation, and complex geometry. Such structures arise in a wide range of

Self-Evaluation Is Already There: Eliciting Latent Judge Calibration in Base LLMs with Minimal Data

arXiv:2606.05122v1 Announce Type: new Abstract: Large language models are increasingly evaluated by other models, raising a natural question: can a model predict how a judge will score its own output?

SemBlock: Semantic Boundary Dynamic Blocks for Diffusion LLMs

arXiv:2606.04964v1 Announce Type: new Abstract: Diffusion language models (DLMs) generate text through iterative denoising, and blockwise decoding improves their practicality by committing tokens in l

Temporal Order Matters for Agentic Memory: Segment Trees for Long-Horizon Agents

arXiv:2606.04555v1 Announce Type: cross Abstract: Long-horizon conversational agents need to interact with users through evolving events, tasks, and goals. Such histories are naturally temporal, yet m

Testing Ideogram JSON prompts in Ernie Image

local-air-stablediffusion

Ideogram 4.0 is a 9.3B open-weight text-to-image model that supports structured JSON prompts enabling control over layout, color, and text placement . Baidu's ERNIE Image is a multilingual text-to-ima

The Biomimetic Architecture of Software 4.0

arXiv:2606.04025v1 Announce Type: cross Abstract: Dominant programming paradigms inherit an execution model optimised for a bygone era of a single human mind instructing a local machine, leaving conte

Towards Estimating Normal and Shear Interface Pressures in Prosthetic Sockets via Least Squares and Mechanics Modeling

arXiv:2606.04222v1 Announce Type: new Abstract: Prosthetic socket fitting remains largely manual and iterative, and objective fit metrics are still limited. Part of the challenge is the lack of long-t

local-aiarxiv-cs-ro

Uncertainty-Aware (Un)Supervised Few-Shot User Adaptation for On-Device Personalized Human Activity Recognition

arXiv:2606.04798v1 Announce Type: new Abstract: Sensor-based Human Activity Recognition (HAR) models often degrade on unseen users due to domain shifts caused by individual movement patterns and senso

v0.30.5

v0.30.5 is a release candidate version of Ollama, a local large language model runner. The v0.30 series features improved compatibility and performance using llama.cpp and augments the MLX engine on A

local-aiollama-releases

VISTA: Vision-Grounded and Physics-Validated Adaptation of UMI data for VLA Training

arXiv:2606.04708v1 Announce Type: cross Abstract: Universal Manipulation Interface (UMI) enables scalable real-world robot data collection without hardware-specific teleoperation, yet leveraging UMI d

Where's gemma4:12b?

Gemma 4 12B is the first medium-sized, encoder-free multimodal model capable of natively ingesting audio and video , recently released by Google. The model is available on Ollama with 11.7M downloads

local-air-ollama

Why Muon Outperforms Adam: A Curvature Perspective

arXiv:2606.04662v1 Announce Type: cross Abstract: Muon improves training efficiency over Adam in large language-model training by about two times, but the local geometric source of this advantage rema

A Geometric Lens on Physics-Aligned Data Compression

arXiv:2606.03279v1 Announce Type: new Abstract: In AI for Science, physics-informed losses are increasingly used to train learned compressors for scientific data, but their rate-distortion implication

A Graph Foundation Model with Spectral Parsing and Prototype-Guided Spatial Propagation

arXiv:2606.03315v1 Announce Type: new Abstract: Graph foundation models aim to learn transferable knowledge from diverse graphs for generalization to unseen graphs and tasks. Unlike text and images, g

A Robust and Explainable Transformer-Based Framework for Phishing Email Detection

arXiv:2511.12085v3 Announce Type: replace-cross Abstract: Phishing and related cyber threats are becoming increasingly sophisticated, with email-based phishing remaining the most persistent attack vec

A unified multi-task framework enables interpretable chest radiograph analysis

arXiv:2606.03417v1 Announce Type: new Abstract: While multimodal deep learning has advanced medical imaging analysis, existing black-box systems extcolor{black}{may remain confined to isolated tasks,

A^2: Smaller Self-Supervised ViTs Localize Better than Larger Ones

arXiv:2606.03148v1 Announce Type: new Abstract: Robust visual classification often depends on localizing the main foreground objects in an image while ignoring contextual distractors. Surprisingly, we

Agent libOS: A Library-OS-Inspired Runtime for Long-Running, Capability-Controlled LLM Agents

arXiv:2606.03895v1 Announce Type: cross Abstract: Large language model (LLM) agents are evolving from request-response assistants into long-running software actors: they maintain state across model ca

ARBOR: Online Process Rewards via a Reusable Rubric Buffer for Search Agents

arXiv:2606.03239v1 Announce Type: new Abstract: LLM-based search agents are trained predominantly with outcome-only reward, leaving the search process itself unsupervised. This signal degenerates on o

Attention, May I Have Your Decision? Localizing Generative Choices in Diffusion Models

arXiv:2604.06052v2 Announce Type: replace Abstract: Text-to-image diffusion models exhibit remarkable generative capabilities, yet their internal operations remain opaque, particularly when handling p

b9487

The search results show general llama.cpp information and references to other recent builds (like b9484), but the specific details for b9487 were not clearly accessible. Based on the context from llam

b9488

Release b9488 of llama.cpp was published on June 3, 2026 , and includes support for Qwen3 SSM architectures with additions like LLM_KV_ATTENTION_RECURRENT_LAYERS . The release also fixes a bug in comm

b9489

Release b9489 of llama.cpp includes updates to hidden_act mapping in llama-model.cpp, additions of granite embedding multilingual R2 models, and support for setting hidden_activation in GGUF files. Th

b9491

b9491 is a release of llama.cpp , a C/C++ implementation of large language model inference that enables running LLMs locally with minimal dependencies. This release likely contains bug fixes, feature

b9493

B9493 is a release of llama.cpp, an LLM inference framework in C/C++ . This release includes updates to model support, such as centralized hidden activation mappings and additions for granite embeddin

b9494

The search results do not contain specific details about the b9494 release. Based on the context from the llama.cpp GitHub releases page, b9494 is an intermediate build release of llama.cpp, a C/C++ p

b9495

The search didn't return specific information about release b9495. Based on the available information about llama.cpp releases, here's a summary: llama.cpp enables LLM inference with minimal setup and

b9496

The search results do not contain specific information about release b9496. Based on the available context, b9496 is a build/release version of llama.cpp, a C/C++ implementation for efficient LLM infe

Before Fusion, Ask What to Keep: Contextual Calibration of Multimodal Signals

arXiv:2606.02679v1 Announce Type: new Abstract: Multimodal systems often benefit from combining information across language, sound, and visual streams, but this benefit is not guaranteed. A modality t

Best ai lipsync for animated characters in 2026?

local-air-stablediffusion

In 2026, leading AI lip-sync tools for animated characters include platforms like Magic Hour, Hedra, Sync.so, and Higgsfield, each optimizing for different approaches such as accurate mouth alignment

CL-DMDF:Dynamic Multimodal Data Fusion Model Based on Contrastive Learning

arXiv:2606.02659v1 Announce Type: cross Abstract: Multimodal data fusion involves integrating and analyzing information from multiple modalities to uncover latent correlations and complementary patter

Coupled Local and Global World Models for Efficient First Order RL

arXiv:2602.06219v2 Announce Type: replace-cross Abstract: World models offer a promising avenue for more faithfully capturing complex dynamics, including contacts and non-rigidity, as well as complex

Cross-Modality Feature Fusion Based on Structured State Space Duality for Multimodal Image Registration Network

arXiv:2606.03341v1 Announce Type: new Abstract: In multi-modal image registration, the primary challenge lies in shared structural information extraction. Compared to Transformers, Structured State Sp

DDOR: Delta Debugging for Explainable Overrefusal Testing and Repair

arXiv:2606.03601v1 Announce Type: cross Abstract: While safety alignment and guardrails help large language models (LLMs) avoid harmful outputs, they can also induce overrefusal, i.e., unwarranted rej

Demystifying Pipeline Parallelism: First Theory for PipeDream

arXiv:2606.03498v1 Announce Type: new Abstract: Training modern machine learning models increasingly requires computation to be distributed across many accelerators. Data parallelism remains the defau

Distill-then-Replace: Efficient Task-Specific Hybrid Attention Model Construction

arXiv:2601.11667v2 Announce Type: replace-cross Abstract: Transformer architectures deliver state-of-the-art accuracy via dense full-attention, but their quadratic time and memory complexity with resp

DMT-CBT: Longitudinal Therapeutic State Modeling for CBT Counseling

arXiv:2606.03132v1 Announce Type: new Abstract: Large language models (LLMs) have shown growing potential for Cognitive Behavioral Therapy (CBT) counseling. However, most existing approaches still for

Edge-Aware and Content-Adaptive Infrared Gas Leak Detection for Industrial Safety Monitoring

arXiv:2512.23234v3 Announce Type: replace-cross Abstract: Infrared gas leak detection is important for industrial safety and environmental monitoring, but automatic detection remains challenging becau

Enhanced Renewable Energy Forecasting using Context-Aware Conformal Prediction

arXiv:2510.15780v2 Announce Type: replace-cross Abstract: Artificial intelligence (AI) is increasingly used to support renewable energy forecasting and grid operations. As renewable penetration grows,

Expert-Aware Causal Tracing of Factual Recall in Sparse MoE Language Models

arXiv:2606.03780v1 Announce Type: new Abstract: Causal tracing of factual recall has been studied predominantly in dense transformer language models, where interventions localize information flow to l

extsc{CR-Seg}: Attention-Guided and CoT-Enhanced Coarse-to-Refined Reasoning Segmentation

arXiv:2606.03564v1 Announce Type: cross Abstract: Reasoning segmentation aims to segment target objects described by complex language through joint visual-textual reasoning. Existing methods typically

FederatedSkill: Federated Learning for Agentic Skill Evolution

arXiv:2606.03143v1 Announce Type: cross Abstract: Modern LLM agents increasingly rely on skill libraries to handle complex tasks, making skill evolution a primary driver of self-improvement. However,

Finding Kissing Numbers with Game-theoretic Reinforcement Learning

arXiv:2511.13391v4 Announce Type: replace-cross Abstract: Since Isaac Newton first studied the Kissing Number Problem in 1694, determining the maximal number of non-overlapping spheres around a centra

FLARE: Fine-Grained Diagnostic Feedback for LLM Code Refinement

arXiv:2606.03852v1 Announce Type: cross Abstract: Large language models often generate code with bugs. Existing methods rely on feedback signals such as test failures and self-critiques to iteratively