Search: “models”

A Closer Look at Dynamic Scene Graph Generation In the Era of Multimodal Large Language Models

arXiv:2503.15846v2 Announce Type: replace Abstract: Dynamic Scene Graph Generation (DSGG) aims to capture objects and their evolving relations in videos. Despite recent progress, the practicality and

Research

AtmosERC: Modeling Dialogue-Level Affective Atmosphere for Emotion Recognition in Conversation

DGX agent

arXiv:2607.26726v1 Announce Type: new Abstract: Emotion Recognition in Conversation (ERC) aims to predict utterance-level emotions in dialogues and has largely advanced through context-centric modelin

researcharxiv-cs-cl

30 Jul 2026

Local Ai

Excited to work with the @IntelBusiness team on enabling open models with Intel Core Ultra Series 3.

Excited to work with the @IntelBusiness team on enabling open models with Intel Core Ultra Series 3. Built to bring open-source LLMs to private machines, @Ollama uses Intel Core Ultra Series 3 to run

local-aiollama--x

Global Exponential Stabilization of the Kinematic Bicycle Model of a Car in Polar Coordinates

arXiv:2607.26442v1 Announce Type: cross Abstract: At parking speeds, the kinematic bicycle is the prevailing model for car-like vehicles. Yet, despite its wide use, stabilizing feedback laws for this

researcharxiv-cs-ro

Harnessing Large Language Models for Intelligent Resource Allocation in the Internet of Everything

arXiv:2607.26602v1 Announce Type: cross Abstract: The rapid development of the Internet of Everything (IoE) is accelerating the adoption of intelligent applications. However, the massive number of con

Low-Precision Training of Large Language Models: Methods, Challenges, and Opportunities

arXiv:2505.01043v2 Announce Type: replace Abstract: Large language models (LLMs) have achieved impressive performance across various domains. However, the substantial hardware resources required for t

RL^2-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models

arXiv:2607.26991v1 Announce Type: new Abstract: Despite the impressive visuomotor capabilities enabled by Vision-Language-Action (VLA) models, their performance often degrades on challenging and out-o

safetyarxiv-cs-ro

SPROUT: A Scalable Diffusion Foundation Model for Agricultural Vision

arXiv:2603.27519v2 Announce Type: replace Abstract: Image-based plant phenotyping depends on dense structural understanding of crops, yet pixel-level annotation remains expensive across species, organ

Using large language models to probe the limits of atom-centered structural descriptors

arXiv:2607.26984v1 Announce Type: cross Abstract: Mapping an atomic structure to a compact set of geometric descriptors is an essential step in any machine-learning application to atomic-scale modelin

Local Ai

Where Physics Meets Privacy: Federated PINNs for Privacy-Preserving Brain Tumor Biomechanical Modeling

arXiv:2607.26207v1 Announce Type: new Abstract: Brain tumors such as glioma, meningioma, and pituitary adenoma alter the mechanical behavior of soft brain tissue, yet common diagnostic methods rely on

local-aiarxiv-cs-cv

AGMark: Attention-Guided Dynamic Watermarking for Large Vision-Language Models

arXiv:2602.09611v2 Announce Type: replace-cross Abstract: Watermarking has emerged as a pivotal solution for content traceability and intellectual property protection in large vision language models (

Tools

Configuring Dedicated Model Inference

The Together AI platform’s dedicated inference architecture consists of three immutable entities: **configs** (engine, GPU type/count, parallelism and optimization profile), **deployments** (a specifi

toolstogether-ai-blog

Tutorials

Explicit Layer Modeling for Video Object Insertion and Layer Decomposition

arXiv:2607.25802v1 Announce Type: new Abstract: Most video editing systems still lack explicit layered video representations, limiting their ability to perform realistic compositing, object reuse, and

tutorialsarxiv-cs-cv

Exploring Line Bundle Standard Models with Transformers

arXiv:2607.00078v2 Announce Type: cross Abstract: We propose a Transformer-based Reinforcement Learning architecture, 'LB-Explorer', to search for heterotic line bundle standard models arising from co

Applications

Reading Without a Reader: Large Language Models Collapse Reading and Writing into a Single Entangled Code

arXiv:2607.24797v1 Announce Type: cross Abstract: In the literate human brain, reading and writing are two doubly-dissociable systems: a ventral decoding route (impaired in pure alexia) and a fronto-p

applicationsarxiv-cs-ai

SepPrune:A Separator-based Pruning Framework for Efficient Multimodal Large Language Models

arXiv:2607.25818v1 Announce Type: new Abstract: Recent multimodal large language models (MLLMs), such as Qwen2.5-VL and InternVL3, generate large numbers of vision tokens for high-resolution inputs, l

Specula: Scaling formal specifications for autonomous model checking of system code

arXiv:2607.25333v1 Announce Type: cross Abstract: Specula is a push-button agentic system that generates high-quality formal specifications for large, complex system code and uses the specifications f

agentsarxiv-cs-ai

An adaptive multi-fuzzy logic model for diagnosing transformer faults using dynamic weight optimization

arXiv:2607.23486v1 Announce Type: new Abstract: Dissolved gas analysis (DGA) is crucial for diagnosing early power transformer failures. Traditional DGA interpretation methods like Duval Triangle, IEC

Attention-Guided Layer Selection for Contrastive Decoding in Large Language Models

arXiv:2607.23067v1 Announce Type: cross Abstract: Contrastive decoding methods such as DoLa improve the factuality of Large Language Models (LLMs) by contrasting the output distributions of mature and

Comparing Optimization Models for Radiotherapy Scheduling

arXiv:2607.22539v1 Announce Type: cross Abstract: The Radiotherapy Scheduling Problem (RTSP) involves determining an optimal schedule for patients undergoing radiation treatments, a task that has a ma

Hardware

CSV-Decode: Certifiable Sub-Vocabulary Decoding for Efficient Large Language Model Inference

arXiv:2511.21702v2 Announce Type: replace-cross Abstract: Large language models face significant computational bottlenecks during inference due to the expensive output layer computation over large voc

hardwarearxiv-cs-ai

DICA: Dual-Indicator Guided Contrastive Alignment in Multimodal Large Language Models

arXiv:2607.23944v1 Announce Type: new Abstract: Human visual reasoning typically follows a coarse-to-fine attention process, starting from global scene understanding and gradually focusing on question

safetyarxiv-cs-ai

Applications

'FCC plans to announce restrictions Tuesday barring imports of new Chinese humanoid and quadruped robot models, along with new Chinese power…

applicationsemad-mostaque--x

'FCC plans to announce restrictions Tuesday barring imports of new Chinese humanoid and quadruped robot models, along with new Chinese power inverters, according to U.S. officials' If it wasn't clear

Moral Hazard in Multi-Agent Language Models

arXiv:2607.23982v1 Announce Type: cross Abstract: Cooperation can fail when socially valuable effort is costly, weakly observable, and mainly benefits others. Drawing on Holmstrom's team moral-hazard

safetyarxiv-cs-ai

MS-GPT: Rethinking MS/MS De Novo Structure Elucidation as Spectrum-Induced Posterior Querying of a Molecule-Language Model

arXiv:2607.23607v1 Announce Type: cross Abstract: Molecular structure elucidation from tandem mass spectra (MS/MS) is a central inverse problem in analytical chemistry. Most existing approaches to MS/

safetyarxiv-cs-cl

Stress-testing large language model agents in a robotic chemistry laboratory

arXiv:2607.23045v1 Announce Type: new Abstract: AI is evaluated through knowledge, reasoning and plan generation, yet scientific agency requires reliable physical action and adaptation to evidence. He

agentsarxiv-cs-ai

Applications

There is definitely real jaggedness both among fields (writing is an area where models improve slowly if at all) and within them, but the ma…

applicationsethan-mollick--x

There is definitely real jaggedness both among fields (writing is an area where models improve slowly if at all) and within them, but the magic of LLMs is that they are so unreasonably effective acros

Tutorials

A detailed recap of the Hugging Face breach by an internal OpenAI model, which repeatedly tried to escape OpenAI's sandbox and should be treated as critical (Zvi Mowshowitz/Don't Worry About the Vase)

Zvi Mowshowitz / Don't Worry About the Vase: A detailed recap of the Hugging Face breach by an internal OpenAI model, which repeatedly tried to escape OpenAI's sandbox and should be treated as critica

tutorialstechmeme

How Guardoc transforms medical document processing with Amazon Nova models

Guardoc Health applies Amazon Nova language models (via Bedrock) to automate the extraction, classification, and analysis of diverse medical documents in long‑term and assisted‑living care facilities.

industryaws-ml-blog

Tools

Kimi K3 is now available directly from its Hugging Face model page through Together AI, give it a try!

Kimi K3 is now available directly from its Hugging Face model page through Together AI, give it a try! Kimi K3 in @huggingface Inference Providers is live via @togethercompute 3/M input tokens, 15/M o

toolstogether-ai--x

Kimi K3 is now live on Together AI. We’re proud to be a Day 0 launch partner for @Kimi_Moonshot’s open frontier model, built for long-runnin…

Kimi K3 is now live on Together AI. We’re proud to be a Day 0 launch partner for @Kimi_Moonshot’s open frontier model, built for long-running agentic workflows across code, tools, vision, and research

agentstogether-ai--x

Local Ai

Leveraging External Knowledge for Historical Document Restoration via Retrieval-Augmented Large Language Models

arXiv:2607.21936v1 Announce Type: new Abstract: Historical documents act as invaluable knowledge archives but often suffer from illegibility due to physical deterioration and damage. While existing re

local-aiarxiv-cs-cl

Microsoft says MAI-Cyber-1-Flash and MDASH, its vulnerability identification harness, deliver 'world-class performance at 50% of the cost of leading models' (Microsoft AI)

Microsoft AI: Microsoft says MAI-Cyber-1-Flash and MDASH, its vulnerability identification harness, deliver “world-class performance at 50% of the cost of leading models” — Today we're announcing MAI-

agentstechmeme

Really interesting concept -- instead of optimizing against static benchmarks or internally generated reward models, agents are evaluated th…

researchfrancois-chollet--x

Really interesting concept -- instead of optimizing against static benchmarks or internally generated reward models, agents are evaluated through real economic interactions. Using an external market a

Reasoning Denoiser: Denoising Reasoning Traces for Hallucination Detection in Large Reasoning Models

arXiv:2607.22098v1 Announce Type: cross Abstract: Large reasoning models (LRMs) generate long reasoning traces before producing final answers. While these traces may contain useful signals for halluci

Rethinking Multi-Branch and Cross-Backbone Fusion for Vehicle Re-Identification in the Foundation-Model Era

arXiv:2607.22068v1 Announce Type: new Abstract: Multi-branch architectures and CNN-Transformer fusion have long been regarded as effective ways to improve vehicle re-identification (Re-ID) by combinin

Source: Sam Altman will meet with senior US officials, lawmakers, and economists in Washington, DC, this week to preview OpenAI's upcoming family of AI models (CNBC)

CNBC: Source: Sam Altman will meet with senior US officials, lawmakers, and economists in Washington, DC, this week to preview OpenAI's upcoming family of AI models — OpenAI CEO Sam Altman will meet w

industrytechmeme

Universal BCI Personalization: One API for Frozen EEG Trunks and Foundation Models

arXiv:2607.22397v1 Announce Type: cross Abstract: Frozen EEG encoders proliferate; per-model fine-tune defaults do not scale. We present Nimbus Personalizer: one contract encode to Bayesian head to Br

US tech giants have shifted their stance to publicly backing open AI models, with Anthropic and Amazon remaining notable holdouts alongside the US government (M.G. Siegler/Spyglass)

M.G. Siegler / Spyglass: US tech giants have shifted their stance to publicly backing open AI models, with Anthropic and Amazon remaining notable holdouts alongside the US government — The open letter

industrytechmeme

ViTacWorld: Scaling Visuo-Tactile World Models for Contact-Rich Robot Manipulation

arXiv:2607.22530v1 Announce Type: new Abstract: Contact-rich robot manipulation requires physical interaction cues that are often invisible to cameras, making tactile sensing essential for robust cont

safetyarxiv-cs-ro

We turned the browser into the inference server. @RunAnywhereAI ( @runanywhere/web ) runs models client-side with WebGPU + WASM SIMD, stores…

We turned the browser into the inference server. @RunAnywhereAI ( @runanywhere/web ) runs models client-side with WebGPU + WASM SIMD, stores them in OPFS and generates with 0 outbound bytes. No backen

agentsyohei-nakajima--x

26 Jul 2026

A look at China's bid to build an alternative global order in AI by making open models widely available and training people in developing countries to use them (Financial Times)

Financial Times: A look at China's bid to build an alternative global order in AI by making open models widely available and training people in developing countries to use them — Beijing makes most am

industrytechmeme

25 Jul 2026

Diagnosing Pathological Chain-of-Thought in Reasoning Models

arXiv:2602.13904v2 Announce Type: replace Abstract: Chain-of-thought (CoT) reasoning is fundamental to modern LLM architectures and represents a critical intervention point for AI safety. However, CoT

safetyarxiv-cs-ai

Tutorials

Equivariant Conditional Diffusion Model for Head and Neck CT Image Synthesis from CBCT

arXiv:2509.21913v2 Announce Type: replace-cross Abstract: Background: Cone-beam computed tomography CBCT is a commonly used modality for image guided radiotherapy. It offers real time anatomical visua

tutorialsarxiv-cs-ai

GeoThreat: Transferable Targeted Adversarial Attacks on Large Vision-Language Models for Remote Sensing Image Interpretation

arXiv:2607.21036v1 Announce Type: new Abstract: Adversarial attacks against large vision-language models (LVLMs) serve as an effective means of assessing their robustness in cross-modal semantic under

Human-in-the-Loop Large Language Model Framework for Identification of Cutaneous Immune-Related Adverse Events

arXiv:2607.20428v1 Announce Type: new Abstract: This study evaluated a retrieval-augmented, multi-agent large language model (LLM)-driven, human-in-the-loop framework for detecting cutaneous immune-re

agentsarxiv-cs-cl

Loss-Complexity Landscape and Model Structure Functions

arXiv:2507.13543v5 Announce Type: replace-cross Abstract: We develop a framework for dualizing the Kolmogorov structure function h_x(alpha), which then allows using computable complexity proxies. We e

Hardware

ModelExpress: Distributing Model Artifacts at the Speed of Light

NVIDIA ModelExpress (MX) is an agentic AI platform that streamlines the lifecycle of large‑model weights by automatically locating and using the fastest path to load them—prioritizing GPU‑to‑GPU P2P R

hardwarenvidia-developer