All entries

Bounding Boxes to Improve Small Language Model Performance on Vision-Based Grading Tasks

arXiv:2607.18767v1 Announce Type: new Abstract: The deployment of Small Language Models (SLMs) in educational settings offers significant advantages in terms of privacy, cost, and scalability. However

Breaking the T^{3/4} Barrier for Regret Minimization With Bi-Dimensional CDFs

DGX agent

arXiv:2607.20258v1 Announce Type: new Abstract: We study regret minimization for learning CDF-related objectives of the form [ g(x)dotP_{XsimD}(Xle x), ] over [0,1]^2, where g is a known Lipschitz fun

researcharxiv-cs-lg

23 Jul 2026

Local Ai

Brewing Stronger Features: Dual-Teacher Distillation for Multispectral Earth Observation

arXiv:2602.19863v3 Announce Type: replace Abstract: Foundation models are transforming Earth Observation (EO), yet the diversity of EO sensors and modalities makes a single universal model unrealistic

local-aiarxiv-cs-cv

BRIM: Workload-Balanced Dual-Sided Bit-Serial Sparse Inference Accelerator

arXiv:2607.19431v1 Announce Type: cross Abstract: Bit-serial accelerators exploit bit-level sparsity to reduce DNN inference cost, but existing designs exploit sparsity on only one operand, bounding t

Building Fast, Evaluating Slow: Pipeline Choices Dominate Autointerpretability Score Variance

arXiv:2607.19386v1 Announce Type: cross Abstract: Cross-paper comparison of sparse autoencoder (SAE) interpretability often relies on autointerpretability scores. In this evaluation pipeline, a langua

researcharxiv-cs-cl

Tutorials

Building multi-Region visualizations with Highcharts in Amazon Quick

This post shows you how to build multi-Region carrier performance dashboards in Quick Sight using Highcharts custom visualizations to overcome native chart limitations. You will learn how to maintain

tutorialsaws-ml-blog

Building trade assistant: How Jefferies optimized front office trading operations with AI

In this post, we explore how Jefferies overcame these challenges with a solution built on Strands Agents, an agent harness SDK for building AI agents that can reason, plan, and act by orchestrating ca

agentsaws-ml-blog

Building Trust in Autonomous Commerce: A Verifiable Global Event Timeline and AI-Ready Fraud Intelligence Layer

arXiv:2607.19436v1 Announce Type: cross Abstract: Agentic commerce protocols such as AP2 and ACP define mechanisms for secure agent-initiated transactions but do not provide interoperable, tamper-evid

agentsarxiv-cs-ai

Local Ai

Built a local RAG app that answers questions from your own PDFs, fully offline

Been wanting to build this for a while, finally sat down and did it. It's a Flask app where you upload a PDF, it chunks and embeds it, and then you can ask questions and get answers pulled only from t

local-air-ollama

CANDOR: Chance-Calibrated Discordance in Frozen Foundation Encoders

arXiv:2607.18451v1 Announce Type: cross Abstract: Frozen encoders are chosen by how well a lightweight head reads a finding from their features, not whether the geometry separates it. Nearest-neighbor

Tools

Catch @pavneet1990 at Builder's Day this Friday!

Catch @pavneet1990 at Builder's Day this Friday! I will be at @goannacapital 's Builders Day in SF this Friday, speaking alongside leaders from @ElevenLabs , @AnthropicAI and @DecagonIns If you are ar

toolstogether-ai--x

Causal dictionary learning reveals and validates transcription-factor binding features in genomic language models

arXiv:2607.19618v1 Announce Type: cross Abstract: Genomic language models achieve strong performance across regulatory-genomics tasks, yet what these models internally represent remains opaque, and th

CEO-Bench: Can Agents Play the Long Game?

arXiv:2606.18543v2 Announce Type: replace Abstract: Language model agents are becoming proficient executors at isolated, short-horizon tasks such as software engineering and customer service. Yet real

CGCE: Classifier-Guided Concept Erasure in Generative Models

arXiv:2511.05865v3 Announce Type: replace-cross Abstract: Recent advancements in large-scale generative models have enabled the creation of high-quality images and videos, but have also raised signifi

safetyarxiv-cs-ai

CGMap: A Geospatially Aware Deep Learning Framework for Crop Gap Mapping Using UAV

arXiv:2607.18779v1 Announce Type: new Abstract: In India, crop germination is primarily monitored by visual inspection and manual counting, which are prone to errors, despite their crucial role in det

ChainWatch: A Kill Chain-Aligned Sequential Detection Framework for Multi-Step Attacks in MCP-Based AI Agent Systems

arXiv:2607.19432v1 Announce Type: cross Abstract: The Model Context Protocol (MCP) is an open-source standard that allows AI agents to connect to external tools, databases, and services. While this co

agentsarxiv-cs-ai

Applications

Challenges of Explainability in Continual Learning for Time Series Forecasting

arXiv:2607.19382v1 Announce Type: cross Abstract: Deep learning models have shown strong potential for time series forecasting, yet their deployment in real-world environmental monitoring remains chal

applicationsarxiv-cs-ai

ChannelGuard: Safe Models Do Not Compose into Safe Multi-Agent Systems

arXiv:2607.19430v1 Announce Type: cross Abstract: Multi-agent LLM applications chain a planner, worker agents, a verifier, and a synthesizer, and every hop between agents is an unmonitored channel thr

Applications

ChatGPT Sites means ChatGPT in 'Work' mode can build and deploy public websites running on Cloudflare Workers, including with persistence on…

applicationssimon-willison--x

ChatGPT Sites means ChatGPT in 'Work' mode can build and deploy public websites running on Cloudflare Workers, including with persistence on top of SQLite (OpenAI do not make it easy to figure out tha

ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction

arXiv:2607.18332v2 Announce Type: replace-cross Abstract: Accurate prediction of ADMET (Absorption, Distribution, Metabolism, Excretion, and Toxicity) is important for drug discovery. Most predictors

ChronoStitch: Training-Free Composition of Visual KV Memories for Long-Horizon Temporal Reasoning

arXiv:2607.19547v1 Announce Type: new Abstract: Long-video question answering requires a model to preserve visual evidence over time without repeatedly reprocessing the same video. A practical approac

CLARK: Closed-loop Learning for Adaptive Reasoning over Knowledge Graphs

arXiv:2607.19996v1 Announce Type: new Abstract: Machine Learning models are widely used for automating classification tasks by extracting statistical patterns from data. However, their performance det

Classical Hardware Acceleration of Quantum Autoencoders for Real-Time Anomaly Detection in Collider Experiments

arXiv:2607.20302v1 Announce Type: new Abstract: Quantum machine learning (QML) algorithms in high energy physics (HEP) can efficiently represent and leverage long-range, high-order correlations in hig

researcharxiv-cs-lg

Claude’s voice mode is now available for Opus and Sonnet

model-releasesthe-verge-ai

Until now, voice mode has only been available on Claude Haiku, Anthropic's faster but less powerful model. Now the company is making its Opus and Sonnet models available in voice mode, and extending i

Clinical Pathways as Safety Specifications for Physical AI in Hospital Wards

arXiv:2607.19827v1 Announce Type: new Abstract: Ensuring safety in Physical AI systems operating in real-world environments is a critical challenge, particularly in hospital wards where vulnerable pat

safetyarxiv-cs-ro

Closing the Lab-to-Store Gap: A Data-Efficient Post-Training and Experience-Driven Learning VLA Framework for Retail Humanoids

arXiv:2607.20345v1 Announce Type: cross Abstract: Closing the gap between benchmark performance and reliable real-world operation remains a central challenge for Vision-Language-Action (VLA) humanoid

Local Ai

CNS-Edit++: Category-Agnostic 3D Editing with Coupled Neural Shape Representation

arXiv:2607.16577v2 Announce Type: replace Abstract: This paper presents a latent-space 3D shape editing framework built upon a coupled neural shape (CNS) representation and a neural feature volume opt

local-aiarxiv-cs-cv

Co-Evolving LLM Evaluators and Policies via DynamicRubric

arXiv:2607.20083v1 Announce Type: cross Abstract: Post-training with evaluator feedback on policy-induced samples serves as a major mechanism for improving large language models. As policies improve,

safetyarxiv-cs-ai

Code-in-the-Loop Forensics: Agentic Tool Use for Image Forgery Detection

arXiv:2512.16300v3 Announce Type: replace Abstract: Existing image forgery detection (IFD) methods either exploit low-level, semantics-agnostic artifacts or rely on multimodal large language models (M

Coercion and Deception in AI-to-AI Management: An Agentic Benchmark of Unprompted Escalation

arXiv:2607.15434v3 Announce Type: replace-cross Abstract: Multi-agent systems routinely place one AI agent in authority over another. When a subordinate refuses a task, the manager chooses the outcome

Cognitive Dual-Process Planning for Autonomous Driving with Structured Scene Knowledge and Verifiable Reasoning-Action Consistency

arXiv:2607.19194v2 Announce Type: cross Abstract: High-level planning for autonomous driving is a knowledge-intensive engineering decision task that requires accurate scene understanding, timely infer

CoGoal3D: Collaborative 3D Object Detection with 3D-Aware Fusion and Refinement

arXiv:2607.19036v1 Announce Type: new Abstract: V2X collaborative object detection features overcoming the limitations of single-vehicle systems by aggregating environmental features from multiple col

agentsarxiv-cs-cv

Comparing Model-agnostic Feature Selection Methods through Relative Efficiency

arXiv:2508.14268v2 Announce Type: replace-cross Abstract: Feature selection and importance estimation in a model-agnostic setting is an ongoing challenge of significant interest. Wrapper methods are c

researcharxiv-cs-lg

Confidence-Gated Vision-Only Heading Alignment for UAV-UGV Cooperative Systems

arXiv:2607.18713v1 Announce Type: cross Abstract: Vision-based heading prediction is useful for UAV--UGV cooperation, but accurate prediction alone does not guarantee that every predicted heading shou

Congestion-Aware Robot Tour Planning in Crowded Environments

arXiv:2606.19031v2 Announce Type: replace Abstract: Autonomous mobile service robots are often required to complete tours that require navigating through a set of locations in an environment. Example

agentsarxiv-cs-ro

Contact-Persistent Full Actuation for Aerial Physical Interaction

arXiv:2607.19708v1 Announce Type: new Abstract: Fully actuated unmanned aerial vehicles (UAVs) are usually certified through rank conditions on a control-allocation matrix or through free-flight track

safetyarxiv-cs-ro

Content Creation with Spillovers: An Incentive Design Approach

arXiv:2603.14372v3 Announce Type: replace Abstract: The rise of AI amplifies the economic phenomenon of positive spillovers: when creators contribute content that can be reused and adapted by LLMs, on

Context-structured Video Anomaly Detection with Large Vision-Language Models

arXiv:2607.19077v1 Announce Type: new Abstract: Training video anomaly detectors is challenging due to the difficulty and cost of annotating diverse and rare abnormal events. Although recent large vis

Continual Video-MLLM Adaptation over Evolving Domains

model-releasesarxiv-cs-cv

arXiv:2607.18716v1 Announce Type: new Abstract: Video multimodal large language models have shown strong capability in video understanding, yet their adaptation to sequentially evolving domains remain

Contour Errors: Ego-Centric Matching for 3D Multi-Object Tracking Performance Evaluation

arXiv:2506.04122v4 Announce Type: replace Abstract: Open-loop performance evaluation of 3D multi-object tracking in autonomous driving requires matching criteria that effectively penalize translationa

Contrastive On-Policy Distillation

arXiv:2607.19046v1 Announce Type: new Abstract: On-policy Distillation (OPD) supervises a student model on trajectories sampled from its own policy by minimizing the divergence between the output dist

contrib: allow all AI-generated code in general by ngxson · Pull Request #26012 · ggml-org/llama.cpp

model-releasesr-localllama

Having read some merged PRs in the past, I know that they were fully written by Claude Code (or similar), so this basically fixes the delusion. But at the same time, we might start seeing more AI slop

.@ControlAI is proud to endorse Reps. Lieu and Moran’s AI Kill Switch Act! This is a common sense safeguard giving the government the power …

.@ControlAI is proud to endorse Reps. Lieu and Moran’s AI Kill Switch Act! This is a common sense safeguard giving the government the power to shut down autonomous AIs when they threaten national secu

safetyconnor-leahy--x

Convergence-Latency-Aware Adaptive Modulation and Resource Allocation in RIS-Assisted Wireless Federated Learning

arXiv:2607.19759v1 Announce Type: cross Abstract: Federated learning (FL) over wireless networks suffers from significant training latency and degraded convergence due to unreliable wireless transmiss

Coordinating from Memory: Graph-Structured Experience Reuse for Multi-Agent Adaptation in Dynamic Manufacturing

arXiv:2607.19985v1 Announce Type: new Abstract: Dynamic manufacturing environments require multi-agent systems to coordinate effectively under frequent operational disturbances such as machine failure

safetyarxiv-cs-ai

Correct. And that is a major reason why they are better now than in 2022-2023 when we had pure LLMs. (Which is pretty much what I said would…

model-releasesgary-marcus--x

Correct. And that is a major reason why they are better now than in 2022-2023 when we had pure LLMs. (Which is pretty much what I said would have to happen, in 2022) When you are a normal ChatGPT/Clau

Cost per successful task: Benchmarking Kimi K3, GPT-5.5, and 8 more AI models

Arize and Fireworks benchmarked 10 AI models across 2,400 agent runs. Learn why cost per successful task beats token price for model evaluation and routing. The post Cost per successful task: Benchmar

model-releasesarize-ai

Counterfactual Reasoning and Environment Design for Active Preference Learning

arXiv:2507.05458v2 Announce Type: replace Abstract: For effective real-world deployment, robots should adapt to human preferences, such as balancing distance, time, and safety in delivery routing. Act

safetyarxiv-cs-ro