Search: “models”

HopRefusalBench: Diagnosing Refusal Failures in Search-Augmented Agents for Multi-Hop Reasoning

arXiv:2608.01358v1 Announce Type: new Abstract: Search-augmented large language model agents are increasingly capable of solving knowledge-intensive tasks, but their behavior when a multi-hop question

Model Releases

Latent-Centroid Steering: Single-Pass Classifier-Free Guidance for Command-Aligned Autonomous Driving

DGX agent

arXiv:2608.00237v1 Announce Type: new Abstract: Vision-language models (VLMs) have recently emerged as a promising paradigm for end-to-end autonomous driving, enabling agents to map multimodal inputs

model-releasesarxiv-cs-cv

4 Aug 2026

Learning What to Remember: Test-Time Training via Context Distillation

arXiv:2608.01672v1 Announce Type: new Abstract: Effective long-context modeling is not merely about retaining more of the past, but about preserving the information that may prove relevant later. Test

Linguistic Context Recodes Visual Representations in Vision-Language Models

arXiv:2608.00035v1 Announce Type: cross Abstract: Goal-directed visual processing is a hallmark of human visual intelligence, resulting in representations that support downstream tasks such as categor

researcharxiv-cs-cv

MedSAM2-Anatomy: Training-Free Inference-Time Optimization for Musculoskeletal Segmentation

arXiv:2608.00195v1 Announce Type: cross Abstract: High-resolution 3D segmentation of hip and shoulder anatomy from CT and MRI is essential for surgical planning, yet frozen segmentation models often f

safetyarxiv-cs-cv

Motion Planning for Mobile Manipulators Navigating Doorways via Model Predictive Control

arXiv:2608.00206v1 Announce Type: new Abstract: Navigating doorways is a fundamental capability for mobile manipulators operating in human environments, requiring coordinated motion between the mobile

researcharxiv-cs-ro

MVHOI: Bridge Multi-view Condition to Complex Human-Object Interaction Video Reenactment via 3D Foundation Model

arXiv:2603.14686v2 Announce Type: replace Abstract: Human-Object Interaction (HOI) video reenactment aims to transfer the interaction dynamics of a source video to a novel target object while preservi

safetyarxiv-cs-cv

Nova: An End-to-End MLIR Compiler for Deep Learning

arXiv:2608.00029v1 Announce Type: cross Abstract: The performance of deep learning models at scale relies heavily on how effectively high-level mathematical operations are mapped to underlying physica

NVIDIA Alpamayo 2 Super, the Frontier Open Model for Robotaxis and Autonomous Vehicles, Now Available for Commercial Use

For robotaxis and other autonomous vehicles (AVs), the hardest problems aren’t the everyday scenarios. They’re the rare, complex situations that are difficult to anticipate and train for. Handling the

hardwarenvidia-blog

ReasonCast: Towards Explainable Time Series Forecasting with Reasoning

arXiv:2608.01875v1 Announce Type: cross Abstract: Most time series (TS) models are specialized for a single task, either understanding (i.e., returning text answers about a TS) or generation (i.e., re

Are the Financial Reasoning from LLMs Credible? A Real World Test over Long-Horizon Statements

arXiv:2607.28661v1 Announce Type: new Abstract: Do Large Language Models (LLMs) possess genuine structural reasoning, or merely rely on surface-level pattern matching? The financial domain, demanding

Local Ai

CoDe-SSM: Context-Detail Decoupled State Space Model for Efficient UHD Image Restoration

arXiv:2607.29595v1 Announce Type: new Abstract: Ultra-high-definition (UHD) image restoration must balance the aggregation of spatially recurring degradation cues with the preservation of localized im

local-aiarxiv-cs-cv

Data Turnstile: A Scalable Open Framework for Function-Calling Data Generation

arXiv:2607.29250v1 Announce Type: new Abstract: Small language models (SLMs) are attractive for agentic deployment due to low latency, reduced cost, and on-device privacy, yet they struggle with tool-

Evaluation-Verification Reward for Consistent Multi-Reference Image Editing

model-releasesarxiv-cs-cv

arXiv:2607.29025v1 Announce Type: new Abstract: While recent image editing models have made rapid progress, multi-reference editing remains challenging, particularly in maintaining visual consistency

Point2Radio: A Foundation Model for Cross-Scene Radio Fields from Material-Aware Point Clouds

arXiv:2607.28994v1 Announce Type: cross Abstract: High-fidelity radio fields are typically simulated for every scene--transmitter configuration or fitted separately to each scene, failing to exploit p

hardwarearxiv-cs-ai

TAPR: Enhancing LLM Performance with a Task-Aware Prompt Rewriter

arXiv:2607.28657v1 Announce Type: new Abstract: Large Language Models (LLMs) often require carefully crafted prompts to unlock their full potential, which can be a barrier for non-expert users. This w

DeepSeek-V4-Flash-0731 is now over 2x faster than yesterday on Ollama's cloud!

DeepSeek-V4-Flash-0731 is now over 2x faster than yesterday on Ollama's cloud! DeepSeek-V4-Flash-0731 is now available on Ollama's cloud. This update substantially enhances the model's agentic capabil

model-releasesollama--x

1 Aug 2026

A Reference-Free Score for Detecting Silent Reasoning Failures in Large Language Models

arXiv:2607.26102v1 Announce Type: cross Abstract: Mathematical chain of thought (CoT) evaluation is commonly reduced to whether the final answer matches a reference. This conflates producing a correct

researcharxiv-cs-ai

Agents

A Robust Placeability Metric for Model-Free Unified Pick-and-Place Reasoning

arXiv:2510.14584v3 Announce Type: replace Abstract: Reliable manipulation of previously unseen objects remains a fundamental challenge for autonomous robotic systems operating in unstructured environm

agentsarxiv-cs-ro

Chimera: Designing and Chinchilla-Scaling Hybrid Visual Diffusion Transformers

model-releasesarxiv-cs-cv

arXiv:2607.28611v1 Announce Type: new Abstract: Visual generation increasingly requires high-resolution images, long videos, and multimodal context, making the quadratic cost of full attention prohibi

Creative Transformation in Literary Texts: Modelling Change Across Representational Levels

arXiv:2607.28513v1 Announce Type: new Abstract: Creativity is often framed as the production of novelty, yet many cultural works emerge through transformation of earlier artifacts and not through isol

safetyarxiv-cs-cl

Echoverse: Deep, Evolving Environments for Training Computer-Use Agents at Scale

arXiv:2607.28074v1 Announce Type: cross Abstract: Computer-use agents learn from what their actions change, so training one needs applications it can act on, break and reset. The applications that mat

Human diversity fuels collective creativity that large language models cannot simulate or sustain

arXiv:2607.26899v1 Announce Type: cross Abstract: Diverse human groups produce diverse ideas, the raw material of innovation. Generative AI challenges this engine twice over: everyday AI assistance ma

researcharxiv-cs-ai

Measuring Alignment With Reader Highlights Net of Position and Length

arXiv:2607.27739v1 Announce Type: cross Abstract: Context compression discards most of a document before a language model reads it, and is normally evaluated by downstream task accuracy - which makes

Region-adaptable retrieval of coastal biogeochemical parameters from near-surface hyperspectral remote sensing reflectance using physics-aware meta-learning

arXiv:2605.05623v2 Announce Type: replace Abstract: Hyperspectral in situ sensing has shown promise in retrieving aquatic biogeochemical (BGC) parameters, such as total suspended solids, dissolved org

Sample More, Reflect Less: Self-Refine and Reflexion Lose to Repeated Sampling at Equal Token Cost, from 1.5B to 7B

arXiv:2607.28576v1 Announce Type: new Abstract: Methods that make a language model plan, criticise and rewrite its own answer, reflect on mistakes, pick the best of several attempts, or debate with co

researcharxiv-cs-cl

Stateless MCP has recaptured my interest (and inspired mcp-explorer and datasette-mcp)

model-releasessimon-willison

Tuesday was Stateless MCP day - the rollout of MCP 2.0, or the 2026-07-28 Model Context Protocol specification to use the more formal but less memorable name. This is the most significant change to th

Local Ai

We applied BitNet-style ternary quantization to a super-resolution transformer. The whole model is 668 KB gzipped and runs in the browser.

local-air-stablediffusion

Everyone's been doing 1.58-bit for LLMs, so we tried it on a vision transformer: Swin2SR (lightweight ×2 variant, 1.01M params), quantized so every weight is −1, 0, or +1 with a small per-group scale

CoCaRS: Correlation Calibration-Based Redundancy Suppression for Heterogeneous Knowledge Distillation

arXiv:2607.27054v1 Announce Type: new Abstract: Knowledge distillation (KD) enables a compact student model to learn from a powerful teacher and has become an effective paradigm for model compression.

Flow Map Learning via Nongradient Vector Flow

arXiv:2607.26398v1 Announce Type: new Abstract: Diffusion and flow-based models benefit from simple regression losses, but inference incurs significant overhead because sampling requires integration.

Genie Sim PanoWorld: An Infinite Indoor 3D World Generation Pipeline via Panoramic Scene Modeling and Simulation

arXiv:2607.26646v1 Announce Type: new Abstract: We address the problem of reconstructing a high-fidelity, freely navigable 3D scene from a single 360^irc panorama, without per-scene optimization or mu

hardwarearxiv-cs-cv

Google reveals Gemini Robotics 2.0, promising improved dexterity and safety

model-releasesars-technica

Google announced Gemini Robotics 2.0 on July 30 2026, launching a family of three models that enhance robot dexterity, safety, and whole‑body intelligence for humanoid machinery. The publicly released

LG AI Research releases K-EXAONE 2.0 750B A37B

model-releasesr-localllama

It was developed under Phase 2 of Korea's Sovereign AI Foundation Model Project. Size: 750B parameters (3x larger than their 236B v1 model). - License: Apache 2.0 Languages: Expanded to 10 language

A Cross-lingual Comparison of Human and Classification Model Entrainment Behavior in Code-switched Speech Settings

arXiv:2607.25202v1 Announce Type: new Abstract: Conversational entrainment is well-studied in monolingual and written contexts, but remains underexplored in spoken code-switching (CSW). We present a n

researcharxiv-cs-cl

Benchmarking Deep Learning Models for Raman Spectroscopy Across Open-Source Datasets

arXiv:2601.16107v2 Announce Type: replace Abstract: Deep learning classifiers for Raman spectroscopy are increasingly reported to outperform classical chemometric approaches. However, their evaluation

researcharxiv-cs-lg

Crystalis: Progressive Nucleation and Semantic Annealing for Coordinated Multi-View Visualization Generation

arXiv:2607.24766v1 Announce Type: new Abstract: Large language models (LLMs) can generate individual charts, but coordinated multi-view visualizations (CMVs), where views share data flows and cross-vi

Freq-RemoteVAR: Next-Frequency Autoregressive Modeling for Remote Sensing Change Detection

arXiv:2607.25815v1 Announce Type: new Abstract: Remote sensing change detection aims to identify land-cover changes from bi-temporal images. Most existing methods follow a one-shot dense prediction pa

researcharxiv-cs-cv

Improving Rare Medication Recommendation with Counterfactual Data Augmentation and Large Language Models

arXiv:2607.24829v1 Announce Type: cross Abstract: AI-based medication recommendation systems have attracted substantial attention due to their potential to enhance patient safety and therapeutic outco

safetyarxiv-cs-lg

Keypoint-Guided Optimal Transport: Models, Algorithms, and Applications

arXiv:2303.13102v2 Announce Type: replace Abstract: Existing Optimal Transport (OT) methods mainly derive the optimal transport plan/matching under the criterion of transport cost/distance minimizatio

safetyarxiv-cs-cv

OrganLens: Organ-Specific Representation Learning for CT Foundation Models

arXiv:2607.25164v1 Announce Type: cross Abstract: A CT examination captures multiple organs, but many biomedical questions concern abnormalities, prognosis, or longitudinal change in a specific organ.

researcharxiv-cs-ai

Tutorials

Reinformed Dreamer: An Asymmetric World Model Efficiently Trained through Latent Guidance

arXiv:2607.26040v1 Announce Type: new Abstract: Much like humans benefit from guidance while learning, reinforcement learning algorithms may benefit from additional supervision beyond rewards. Leverag

tutorialsarxiv-cs-lg

Tokenizing Numerical and Embedding Features for LLM RecSys

arXiv:2607.10016v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly used as backbone architectures for recommender systems because of their strong sequence modeling

Unlocking Spatial Grounding in Large Audio-Visual Retrieval models

arXiv:2607.24786v1 Announce Type: cross Abstract: Weak supervision sets a practical regime for audio-visual sound source localization as dense spatial annotations are costly to obtain at scale. The ta

safetyarxiv-cs-ai

Industry

AI researchers call for new tools that can slow automated model development

A group of tech workers today published an open letter that calls for a new approach to regulating automated artificial intelligence development initiatives. All the document’s 1,134 signatories work

industrysiliconangle

Appreciation for Gemma 4 26b A4b

model-releasesr-localllama

I really love this model, I have been using the q4_k_l by Bartowski (I have heard QAT is quite the downgrade in some aspects) and it handles every task I throw at it easily. Agentic and coding perform

Beyond Shapley: An Influence-Based Data Auditing Pipeline for LLM Alignment and Evaluation

arXiv:2607.22766v1 Announce Type: cross Abstract: The alignment of Large Language Models (LLMs) is increasingly bottlenecked by data quality. As datasets scale, massive preference and instruction-tuni

ClinFusion: A Vision-Centric Multimodal LLM System for Holistic Medical Understanding

arXiv:2607.24743v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) hold immense potential to revolutionize clinical practice, yet deploying them in the medical domain is fundam

Evo-DKD: Dual-Knowledge Decoding for Autonomous Ontology Evolution in Large Language Models

arXiv:2507.21438v2 Announce Type: replace Abstract: Ontologies and knowledge graphs require continuous evolution to remain comprehensive and accurate, but manual curation is labor intensive. Large Lan

hardwarearxiv-cs-ai