Search: “models”

Made this game in two prompts with Q4, Qwen 3.8 is amazing

model-releasesr-localllama

This took one prompt to build, and another follow up prompt to fix two issues (player got stuck with the bomb and broken enemies path-finding), this is only html, css and js, no external assets, all d

MAPLE: MoE Adaptive Plug-and-play Layer-wise Expert allocation

DGX agent

arXiv:2608.15299v1 Announce Type: cross Abstract: Sparsely-activated Mixture-of-Experts (MoE) Transformers universally fix the same number of routed experts across all layers, a convention that ignore

model-releasesarxiv-cs-ai

18 Aug 2026

Matched Outcomes, Divergent Gaze: How Foveated MLLMs Search Compared to Humans

arXiv:2608.16514v1 Announce Type: cross Abstract: Human visual search is serial: the fovea must land on a candidate to confirm it, and those landings form a scanpath. Whether multimodal large language

safetyarxiv-cs-ai

MiDAS: A Multimodal Data Acquisition System and Dataset for Robot-Assisted Minimally Invasive Surgery

arXiv:2602.12407v3 Announce Type: replace-cross Abstract: Background: Robot-assisted minimally invasive surgery (RMIS) research increasingly relies on multimodal data, yet access to proprietary robot

MiNO: Cotangent-bundle propagator learning for PDEs

model-releasesarxiv-cs-lg

arXiv:2608.15187v1 Announce Type: new Abstract: Scientific machine learning for partial differential equations commonly targets solution fields, as in physics-informed neural networks, or solution map

MITE-Net: SWaP-Optimized 4K Video Tiny Target Perception for Embodied Edge SAR

arXiv:2608.15830v1 Announce Type: new Abstract: Real-time tiny target perception in high-resolution imagery is critical for embodied Search-and-Rescue (SAR) missions. However, strict Size, Weight, and

MOSS-VL Technical Report

arXiv:2608.15045v1 Announce Type: new Abstract: We present MOSS-VL, an open vision-language model family that treats real-time interaction -- perceiving while it speaks -- as a first-class capability.

researcharxiv-cs-cv

Local Ai

mR^2AG: Multimodal Retrieval-Reflection-Augmented Generation for Knowledge-Based VQA

arXiv:2411.15041v2 Announce Type: replace Abstract: Advanced Multimodal Large Language Models (MLLMs) struggle with recent Knowledge-based Visual Question Answering (VQA) tasks, such as INFOSEEK and E

local-aiarxiv-cs-ai

NARRATE: A Multimodal Real-World Australian Driving Dataset for Human-Centred Explanations in Automated Driving

arXiv:2608.14767v1 Announce Type: cross Abstract: Automated vehicles must explain their decisions in ways that passengers can understand, monitor, and trust. Existing language-annotated driving datase

Not All History Helps: Velocity-Aware Selective Memory for Long-Horizon End-to-End Autonomous Driving

model-releasesarxiv-cs-ro

arXiv:2608.15573v1 Announce Type: new Abstract: Reliable long-horizon planning remains a key challenge in end-to-end autonomous driving. By accounting for future motion evolution and potential consequ

Path2ST: Hierarchical Cell-Tissue Grounded Cross-Modal Translation for Spatial Transcriptomics

arXiv:2608.14710v1 Announce Type: cross Abstract: Predicting spatial gene expression from hematoxylin and eosin (H&E)-stained images offers a cost-effective alternative to spatial transcriptomics (ST)

PerFACT: Motion Policy with LLM-Powered Dataset Synthesis and Fusion Action-Chunking Transformers

model-releasesarxiv-cs-ro

arXiv:2512.03444v2 Announce Type: replace Abstract: Deep learning methods have significantly enhanced motion planning for robotic manipulators by leveraging prior experiences within planning datasets.

PersonaShot: Benchmarking Person-Centric Narrative Continuity in Multi-Shot Video Generation

arXiv:2608.16717v1 Announce Type: new Abstract: Video generation is rapidly evolving from single-shot clips to multi-shot narratives, where the human character serves as the core narrative anchor. How

PhaseLoRA: Control-Regime-Conditioned Low-Rank Adaptation for Continuous-Action Vision-Language-Action Policies

arXiv:2608.15285v1 Announce Type: cross Abstract: Parameter-efficient fine-tuning (PEFT) is a natural way to adapt pretrained vision-language-action (VLA) policies, but most adapter designs apply temp

pico-type: A 1.5M-Parameter Byte-Level Multi-Head Content Classifier

arXiv:2608.14658v1 Announce Type: cross Abstract: We introduce pico-type, a byte-level multi-head content classifier with approximately 1.5 million parameters that simultaneously predicts seven conten

Position: Evaluations of AI Moral Reasoning Still Miss Half of the Picture

arXiv:2608.14566v1 Announce Type: new Abstract: Recent work on evaluating the moral competence of large language models (LLMs) has focused primarily on what we call the moral value problem, i.e., whet

PosterText: Towards Unified Visual Text Generation and Editing for E-commerce Poster

arXiv:2608.16289v1 Announce Type: new Abstract: Automated e-commerce poster design requires both high-quality poster generation and flexible editing of existing designs. However, most existing methods

Projection-based multifidelity linear regression for data-scarce applications

arXiv:2508.08517v2 Announce Type: replace-cross Abstract: Surrogate modeling for systems with high-dimensional quantities of interest remains challenging, particularly when training data are costly to

researcharxiv-cs-lg

Pushing the Limits of High-Resolution Weather Forecasting through Data Scaling

arXiv:2608.14652v1 Announce Type: cross Abstract: The development of 0.1^{irc} global weather forecasting models based on machine learning (ML) is constrained by the limited availability of high-resol

Quipu: A Governed Bitemporal Knowledge Graph Store

arXiv:2608.16813v1 Announce Type: new Abstract: Agents now write knowledge graphs, but knowledge-graph stores still carry defaults set when humans curated them: accept writes now and clean later, keep

ReRef-3D: A Benchmark for Spatial Referring Expression-Guided 3D Scene Rearrangement

model-releasesarxiv-cs-cl

arXiv:2608.16011v1 Announce Type: new Abstract: We introduce ReRef-3D, a benchmark for language-guided placement in 3D scenes. It contains 33,826 instructions across 998 CLEVR-derived scenes, spanning

RRFC: Recursive Refinement via Feedback Conditioning for Iterative Image-to-Image Generation

arXiv:2608.15694v1 Announce Type: cross Abstract: Conditional image-to-image generators are single-shot: they map input features to an output in one forward pass and treat it as final, with no opportu

Scaling Manual-Grounded Appliance Manipulation with Data Synthesis and Unified Planning

arXiv:2608.15863v1 Announce Type: cross Abstract: Operating household appliances requires long-horizon planning that is state-dependent and robust to disturbances, yet existing large models fall short

SMOPD: Selective Token-Entropy Masking for Dirty-History Multi-Turn On-Policy Self-Distillation

arXiv:2608.14647v1 Announce Type: cross Abstract: Dirty-history rollouts make multi-turn on-policy self-distillation (OPSD) brittle: once a student emits an erroneous intermediate reply, later turns a

Sparse Prototype Code Underlies Classification and Prediction Across Modalities

arXiv:2608.15632v1 Announce Type: cross Abstract: Neural representations have become a central tool for studying the internal mechanisms of modern AI models, yet their complex high-dimensional structu

Agents

Spatial Attention Noise Masking for Causally Sufficient Interpretability

arXiv:2608.14725v1 Announce Type: new Abstract: We present a novel causal approach to interpretability for computer vision models that dynamically masks the input image prior to classification. The in

agentsarxiv-cs-cv

Spatial Temporal Synergy: Balancing Change and Invariance in Text Driven 3D Human Motion Editing

arXiv:2608.16008v1 Announce Type: new Abstract: Text-driven human motion editing aims to modify existing motion sequences according to natural language instructions while maintaining the structural co

Spatially-Grounded Flow Matching: Structured Source Distributions for Image Generation

arXiv:2608.15452v1 Announce Type: new Abstract: Current flow matching models learn to transport the source i.i.d. Gaussian noise into the target distribution of natural images, yet this source distrib

safetyarxiv-cs-cv

Stitch the Fragments: One-Shot Hierarchical Federated Clustering

model-releasesarxiv-cs-lg

arXiv:2601.06404v2 Announce Type: replace Abstract: Federated Clustering (FC) faces a critical bottleneck in real-world scenarios, i.e., global clusters are rarely intact, often fragmenting into incom

Strong enough to keep up with the frontier, light enough to run on your own laptop. Come see what it can do! ⚡

Strong enough to keep up with the frontier, light enough to run on your own laptop. Come see what it can do! ⚡ It's official: Qwen3.8-27B just scored 52 on the @ArtificialAnlys Intelligence Index. We

model-releasesqwen--x

Structured Prediction for Scalable Spreadsheet Table Understanding: From Cell Types to Table Ranges (Extended Version)

model-releasesarxiv-cs-lg

arXiv:2608.16050v1 Announce Type: cross Abstract: Spreadsheets are a primary medium for publishing tabular data, yet automatically extracting structured content from them remains difficult due to hete

Tactile Sim2Real without Tactile Simulation via Bottlenecked Latent Reconstruction

arXiv:2608.15897v1 Announce Type: new Abstract: Robot sensor designs, particularly tactile sensors, are highly diverse and evolve rapidly. Modeling each sensor in simulation demands substantial domain

safetyarxiv-cs-ro

TaoLive Digital Avatar Agent Technical Report: Training Agents to Evolve with Their Harness

arXiv:2608.15763v1 Announce Type: new Abstract: AI-powered digital-avatar streamers in live e-commerce must answer product questions, engage viewers, and execute changing business strategies in real t

safetyarxiv-cs-cl

The Machine's Internal Clock: Do LLMs Share Human Temporal Illusions?

model-releasesarxiv-cs-cl

arXiv:2608.15394v1 Announce Type: new Abstract: Human perception of time is subjective. Well-documented temporal illusions show that the brain relies on context and relational cues for judging duratio

The Quality of Claude AI-authored Python Tests Is Not Weaker Than Human-authored Tests

arXiv:2608.15188v1 Announce Type: cross Abstract: We evaluate the quality of Claude AI-written Python tests against human-written Python tests from two established open-source projects Django and Pand

the real unlock is not cheaper evaluation it is making specialized evaluators cheap enough to run continuously on production traces so evalu…

model-releasesharrison-chase--x

the real unlock is not cheaper evaluation it is making specialized evaluators cheap enough to run continuously on production traces so evaluation stops being a launch checklist and becomes a permanent

TISC: A Text-Driven Image Semantic Communication System for Faithful Reconstruction

arXiv:2608.16100v1 Announce Type: new Abstract: Generative image semantic communication converts an image into a text description and then performs text-to-image reconstruction at the receiver via dif

Towards Computational Provenance: Carrying Causal-State Evidence in Generated Text

arXiv:2608.16868v1 Announce Type: cross Abstract: A language model's output does not by itself provide verifiable evidence about the internal computation that produced it. We study computational prove

Local Ai

TRACE-Bench: Decomposing and Diagnosing Multi-Reference Image Generation

arXiv:2608.16765v1 Announce Type: cross Abstract: Despite recent advances in unified multimodal models for multi-reference image generation, existing benchmarks remain organized around predefined task

local-aiarxiv-cs-ai

TRACE: Trajectory Aware Reasoning for Multi-Turn Adversarial Conversation Evaluation

arXiv:2608.15594v1 Announce Type: new Abstract: Multi-turn jailbreak attacks have emerged as a critical safety threat to LLMs, as harmful objectives are decomposed across a sequence of apparently beni

Applications

Unlocking the Potential of Image Editing via Concept Scaling and Dense Supervision

arXiv:2608.16812v1 Announce Type: new Abstract: Existing image editing frameworks predominantly follow the training paradigm of text-to-image diffusion models. However, extending this paradigm to imag

applicationsarxiv-cs-cv

Valhalla: A Layered Knowledge-State and Service-Governance Framework for Long-Term Scientific Knowledge Work

arXiv:2608.15193v1 Announce Type: cross Abstract: As large language model (LLM) agents are increasingly adopted in scientific research, external knowledge bases, knowledge graphs, and long-term memory

Agents

WARA: Toward Automated Wireless Optimization Research with Closed-Loop LLM Agents

arXiv:2608.14573v1 Announce Type: cross Abstract: Large language model (LLM) agents are increasingly capable of tool use, code execution, artifact inspection, and iterative revision, creating new oppo

agentsarxiv-cs-ai

Who Leads Now? Token-Level Modality Arbitration for Chart-to-Code Generation

arXiv:2608.15510v1 Announce Type: new Abstract: Chart-to-code generation requires a model to read the fine-grained visual details of a chart and write executable code that reproduces it. Existing char

A Calibrated Test of Internal Action Maps: State Signals Without Global Affine Closure

arXiv:2608.13626v1 Announce Type: new Abstract: A hidden state signal can be decodable or causally usable without supporting a reusable action map. We test whether action maps fitted without a source

AgentRewind: Recoverable Execution for Long-Horizon LLM Agents

arXiv:2608.14380v1 Announce Type: new Abstract: Many real-world tasks require LLM agents to interact with their environments over long execution horizons. Errors that occur early in execution may prop

AI-Assisted Discovery and Construction of a Counterexample to the Convergence of Three-Block ADMM with the Identity Matrix as its Third Constraint Block

arXiv:2608.14396v1 Announce Type: cross Abstract: The alternating direction method of multipliers (ADMM), as a landmark algorithm, has attracted tremendous research attention and extensive practical a

Anthropic's text watermark alters word probabilities to embed a fingerprint, which could degrade Claude's writing, despite its claim of no impact on quality (John Gruber/Daring Fireball)

John Gruber / Daring Fireball: Anthropic's text watermark alters word probabilities to embed a fingerprint, which could degrade Claude's writing, despite its claim of no impact on quality — When I wro

model-releasestechmeme