Search: “model-releases”

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

Model Releases

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

DGX agent

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

model-releasesarxiv-cs-ai

23 Jul 2026

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

Continual Video-MLLM Adaptation over Evolving Domains

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

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

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

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

CPU-only inference on a Celeron N5095 SBC: 6 models from 0.6B to 8B, benchmarked

I wanted to know how cheap you can go and still run local models, so I ran Ollama CPU-only on a Youyeetoo X1S. It's a single-board x86 machine with a Celeron N5095 (Jasper Lake, 4C/4T, 15W), 16GB of R

CR-Refiner: An Object-Centric Optimal Transport Reranker for Edit-Conditioned 3D Scene Retrieval

arXiv:2607.19115v1 Announce Type: new Abstract: Edit-conditioned 3D scene retrieval pairs a reference 3D room with a natural-language modification and retrieves rooms from a corpus that satisfy the ed

CrackedPDFs: A Controlled Benchmark for Hidden Prompt Injection in PDFs

arXiv:2607.19396v1 Announce Type: new Abstract: Document-based LLM systems often flatten a PDF before guardrails inspect it. That step can discard evidence that an instruction was never visible to the

CreatiPoster: Towards Editable and Controllable Multi-Layer Graphic Design Generation

arXiv:2506.10890v2 Announce Type: replace Abstract: Graphic design plays a crucial role in both commercial and personal contexts, yet creating high-quality, editable, and aesthetically pleasing graphi

Cross-Modal UAV Object Tracking: State-Aware Representation Learning and A Unified Benchmark

arXiv:2607.18768v1 Announce Type: new Abstract: Unmanned Aerial Vehicle (UAV) object tracking has emerged as a popular research field with broad practical applications. Modern UAVs are increasingly eq

CruiseBench: A Real-Flight-Aligned N-CMAPSS Benchmark for Engine RUL Prediction

arXiv:2607.19380v1 Announce Type: new Abstract: Remaining useful life (RUL) prediction estimates how long an engine can continue safe operation and is central to maintenance planning. N-CMAPSS extends

Cumsum-Composable Phase Transport for Low-Cost Streaming Keyword Spotting

arXiv:2607.20086v1 Announce Type: cross Abstract: State-space sequence models are attractive for streaming speech because they maintain compact recurrent state, but scan-style training kernels can hav

Current Injection Spiking Neural Network for Infrared and Visible Image Fusion

arXiv:2607.19879v1 Announce Type: new Abstract: Infrared and visible image fusion (IVIF) integrates the complementary information of two modalities into a single image with richer scene content. While

D2VBench: Benchmarking Large Language Models with Value Dilemmas in Daily Scenarios

model-releasesarxiv-cs-cl

arXiv:2607.19834v1 Announce Type: new Abstract: With the wide application of large language models (LLMs) in real-world scenarios, the value implication of their outputs is crucial. However, existing

Decodable but Not Detectable: A Leakage Fingerprint for Near-OOD Benchmarks

arXiv:2607.19393v1 Announce Type: cross Abstract: While auditing a perturbation-based OOD detector on a document benchmark, we recorded an AUROC of 0.326 -- well below the 0.5 chance level. The cause

DeepSeek Founder’s 4-hour investor meeting: DeepSeek is prioritizing AGI over user growth and commercialisation

A Chinese article compiled 52 remarks from Liang Wenfeng’s four-hour investor meeting. I’ve summarised the most important ones below. DeepSeek has one central objective: AGI. This is not the time to m

Deepseek V4 Flash ~105 t/s on two Nvidia 4090d 48G (ada) in vLLM

TLDR: I (with the help of AI) re-implemented every Blackwell-only kernel (DeepGEMM, FlashInfer sparse-MLA, block-scaled FP8) in Triton, because they simply don't exist for sm89. The performance is 2-3

Defense Against LLM Backdoors using Critical Neuron Isolation Pruning

arXiv:2607.19894v1 Announce Type: cross Abstract: Large language models (LLMs) are vulnerable to backdoor attacks, where hidden triggers induce malicious outputs. Existing defenses generally fall into

Delineate Anything v2: A Global Foundation Model for Field Delineation

arXiv:2607.19069v1 Announce Type: new Abstract: Accurate agricultural field boundary delineation at large scale is a foundational task for food security, supply chain transparency, and carbon accounti

Diffusion ReRoll: Revisable Denoising for Robotic Sequential Prediction

arXiv:2607.19919v1 Announce Type: cross Abstract: We propose Diffusion ReRoll, a diffusion-based framework for robotic sequential prediction that enables revisable denoising over horizons. Existing di

Diverse-Intent Multi-Turn Fashion Image Retrieval

arXiv:2607.20291v1 Announce Type: new Abstract: Real-world fashion search involves interactive retrieval across multiple turns. However, existing multi-turn retrieval methods are built on a restrictiv

DobicVLM: Aligning Chest X-Ray Report Generation with Clinically-Grounded Programmatic Rewards via Group Relative Policy Optimization

arXiv:2607.18988v1 Announce Type: new Abstract: Medical imaging is a cornerstone of diagnostics, yet automated chest X-ray report generation struggles with structural adherence, anatomical completenes

DocOps: A Verifiable Benchmark for Autonomous Agents in Complex Document Operations

arXiv:2607.19865v1 Announce Type: new Abstract: As autonomous agents rapidly evolve, their ability to reliably manipulate ubiquitous digital documents has become critical for enabling general-purpose

DocShield: Towards AI Document Safety via Evidence-Grounded Agentic Reasoning

arXiv:2604.02694v2 Announce Type: replace-cross Abstract: The rapid progress of generative AI has enabled increasingly realistic text-centric image forgeries, posing major challenges to document safet

Dominant vs. Dominated: Concept-Level Generative Collapse in Diffusion Models

arXiv:2512.20666v2 Announce Type: replace-cross Abstract: Text-to-image diffusion models have attracted significant attention for their ability to generate diverse, high-fidelity images. However, in m

DQAOA-GPT: AI-Accelerated Distributed Quantum Optimization for Combinatorial Problems

arXiv:2607.20225v1 Announce Type: cross Abstract: While combinatorial optimization problems are central to many scientific and engineering applications, their solution remains challenging due to expon

DREMnet: An Interpretable Denoising Framework for Semi-Airborne Transient Electromagnetic Signal

arXiv:2503.22223v2 Announce Type: replace Abstract: The semi-airborne transient electromagnetic method (SATEM) is capable of conducting rapid surveys over large-scale and hard-to-reach areas. However,

DRGBT-1K: A Large-scale High-quality Benchmark for Dynamic RGBT Tracking

arXiv:2607.19772v1 Announce Type: new Abstract: Dynamic RGBT (DRGBT) tracking aims to continuously localize a target when the available sensing modalities and observation platforms vary over time. Com

Dynamic workflows are a generalization of harnesses, automations, loops, routing, and graphs. It's the most powerful feature I have built in…

Dynamic workflows are a generalization of harnesses, automations, loops, routing, and graphs. It's the most powerful feature I have built into my agent orchestrator. Supports all kinds of patterns tha

model-releasesdair-ai--x

ECoNGS: Efficient Compressive Neural Gaussian Splats for Volume Visualization

arXiv:2607.18466v1 Announce Type: new Abstract: Recent advances in differentiable Gaussian splatting have highlighted the potential of primitive-based approaches as alternative scene representations f

Economic Evaluations of Language Models

arXiv:2607.19375v1 Announce Type: cross Abstract: Language models perform economically valuable work, yet they are not currently assessed for how well they perform every economically valuable task. We

Emergent Autonomous Drifting for Collision Avoidance in Real-World Winter Driving Scenarios

model-releasesarxiv-cs-ro

arXiv:2607.19484v1 Announce Type: new Abstract: Real-world collision avoidance is a core motivation for studying the dynamics and control of high sideslip drifting in vehicles, yet the practical benef

Enhancing LLMs for Identifying and Prioritizing Important Medical Jargons from Electronic Health Record Notes Utilizing Data Augmentation: A Comparative Study

model-releasesarxiv-cs-cl

arXiv:2502.16022v3 Announce Type: replace Abstract: OpenNotes gives patients access to their EHR notes, but dense medical jargon limits comprehension. We evaluate closed-source and open-source LLMs fo

ENTRAP-VL: A Taxonomic Probe for Dual Contextual Entrainment in Vision-Language Models

arXiv:2607.20092v1 Announce Type: cross Abstract: Contextual entrainment is the tendency of a model to let auxiliary context in its input pull its output, independently of whether that context is rele

ETPDesigner: Multi-Agent Orchestration for Interactive Multimodal Electronic Theater Program

arXiv:2607.19947v1 Announce Type: new Abstract: Electronic Theater Programs (ETPs) serve as critical promotional media in the performing arts, comprising a multi-page collection of heterogeneous visua

EvoDRC: A Self-Evolving Agentic Framework for Automated DRC Violation Repair

arXiv:2607.20019v1 Announce Type: new Abstract: Design rule check (DRC) closure remains a major bottleneck in advanced-node physical design. Although detailed routers are rule-aware, residual design r

ExpertVerse: A General-Purpose Benchmark for Expert-Level Reasoning in Knowledge-Intensive Visual Synthesis

arXiv:2607.19341v1 Announce Type: new Abstract: Recent advances in multimodal generative models have enabled instruction-based image generation to move beyond semantic manipulation to knowledge-driven

FedCC: A Low-Resource Federated Adaptation of Foundation Models for Robust Corpus Callosum localization in Fetal Ultrasound Images

arXiv:2607.18283v1 Announce Type: cross Abstract: Accurate localization of the corpus callosum (CC) in fetal ultrasound (US) images is crucial for the early identification of neurodevelopmental abnorm

FilmWorld: Agentic Novel-to-Film Generation through Dynamic Cinematic World Modeling

arXiv:2607.19038v1 Announce Type: new Abstract: Translating novels into films poses a grand challenge for generative artificial intelligence, requiring conversion of abstract literary prose into long-

Fine-grained Computation-Communication Overlap via Tile-level Signaling and Scheduling for Mixture-of-Experts

arXiv:2607.19539v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) architectures increase model capacity without proportionally increasing computation cost and have become a key building block

Fluid-SDF: Ultra-Lightweight and Editable Implicit Shape Representation via Differentiable Primitives

arXiv:2607.18646v1 Announce Type: new Abstract: Implicit Neural Representations (INRs) have become the standard for continuous 2D shape modeling, but they suffer from black-box uneditability, vulnerab

FORCE-Bench: A Benchmark, Dataset, and Evaluation Harness for Agentic AI in Enterprise Finance

arXiv:2607.19409v1 Announce Type: new Abstract: Recent advances in large language models have accelerated deployment of agentic systems in operational finance. Existing benchmarks emphasize measuring

Frequency-Hierarchical Active k-Space Sampling for Diagnostic MRI

arXiv:2607.19779v1 Announce Type: new Abstract: Active sampling for accelerated MRI must distribute a tight sampling budget across spatial frequencies that carry very different kinds of information. L

FreyaTTS: A Compact Tokenizer-Free Flow-Matching Transformer for Turkish-First Speech Synthesis

model-releasesarxiv-cs-cl

arXiv:2607.09530v2 Announce Type: replace Abstract: We introduce Freya-TTS, a compact, tokenizer-free, Turkish-first text-to-speech model designed for highly reliable and efficient conversational synt

FYI You dont need expensive networking for multi-node gpu. 30t/s laguna Q2_K_XL (39.7GB) on 2x4060+1x4060 using a $20 usb->ethernet.

Turns out a regular ethernet cable between 2 nodes can run laguna UD-Q2_K_XL (39.7GB) using a direct point to point network. Interestingly on `nvidia-smi dmon -s pucvmet -d 2`, the inter/intra gpu tra

G-MAD: A Game-Based Data Generation Framework for Multi-View RGB-T Aerial Object Detection

arXiv:2607.19942v1 Announce Type: cross Abstract: This work introduces G-MAD, an open-source framework that uses Arma3 to generate synchronized multi-view RGB-T data for aerial object detection. G-MAD