Search: “model-releases”

GATE-3D: Geometry-Aware Test-time Adaptive Reranking for Open-Set 3D Shape Retrieval

arXiv:2607.19111v1 Announce Type: new Abstract: Large pretrained vision models have substantially improved appearance-based 3D shape retrieval, but they still confuse shapes that look similar while di

Model Releases

Generative AI-enhanced Probabilistic Multi-Fidelity Surrogate Modeling Via Transfer Learning

DGX agent

arXiv:2602.00072v2 Announce Type: replace Abstract: The performance of machine learning surrogates is critically dependent on data quality and quantity. This presents a major challenge, as high-fideli

model-releasesarxiv-cs-lg

23 Jul 2026

Geometry-Guided Constraint Learning for LLM Safety Classification

arXiv:2607.19366v1 Announce Type: new Abstract: Safety as Polytope (SaP) learns linear half-space constraints in LLM hidden space but requires per-category tuning of the constraint count K. We show th

Germany's Black Forest Labs launches Flux 3 and Flux-mimic, its first models for robotics, as it expands from generative AI into physical AI (Yazhou Sun/Bloomberg)

Yazhou Sun / Bloomberg: Germany's Black Forest Labs launches Flux 3 and Flux-mimic, its first models for robotics, as it expands from generative AI into physical AI — Black Forest Labs, a German artif

model-releasestechmeme

GH-ESD: Grounded Hypothesis-Driven Error Slice Discovery for Instance-Level Vision Tasks

arXiv:2512.24592v3 Announce Type: replace Abstract: Systematic failures of vision models on semantically coherent subsets, known as error slices, reveal limitations in robustness and evaluation. Exist

GLID: Gated Local Intrinsic Dimension Repairs the Blind Spots of Face-Forgery Detectors

arXiv:2607.18770v1 Announce Type: cross Abstract: Fine-tuned foundation-model detectors dominate face-forgery benchmarks, yet they stay blind to generator families absent from training. We present GLI

Good Practice Guide for quantifying uncertainties for machine learning models applied to photoplethysmography signals

arXiv:2607.19999v1 Announce Type: new Abstract: This Good Practice Guide presents work done in the QUMPHY project (Uncertainty quantification for machine learning models applied to photoplethysmograph

GPT-5.5 Scores 10.6% on ActiveVision, Humans Hit 96.1% [R]

model-releasesr-machinelearning

The interesting finding from a new [arXiv paper](https://arxiv.org/abs/2607.16165) isn't that a frontier vision model failed a new benchmark, that happens weekly, but the specific shape of the failure

Great paper on self-improving agent harnesses. (bookmark it) If you maintain a production agent harness, finding every file behind one behav…

Great paper on self-improving agent harnesses. (bookmark it) If you maintain a production agent harness, finding every file behind one behavior is often harder than writing the edit. Harness Handbook

model-releasesdair-ai--x

HalluTruthQA: A Fine-Grained Benchmark for Hallucination Detection, Localization, and Explanation in Arabic Question Answering

model-releasesarxiv-cs-cl

arXiv:2607.20219v1 Announce Type: new Abstract: Large language models (LLMs) can generate fluent Arabic answers, yet factual errors remain difficult to detect, localize, explain, and verify. Existing

Health in ChatGPT is starting to roll out to U.S. users. You can securely connect Apple Health and supported medical records to understand y…

Health in ChatGPT is starting to roll out to U.S. users. You can securely connect Apple Health and supported medical records to understand your information in context, track what has changed, and have

model-releasesopenai--x

Hybrid LLM-Guided Search for Quantum Reservoir Architecture Design

arXiv:2607.19506v1 Announce Type: cross Abstract: Quantum reservoir computing (QRC) uses fixed quantum dynamics as a high-dimensional temporal feature map and trains only a lightweight classical reado

HypEMBER: Hypernetwork-based Ensemble for Robust Policy Learning of Parametrized Dynamical Systems

arXiv:2607.19628v1 Announce Type: new Abstract: In this work we investigate reinforcement learning (RL) as a framework for the robust control of parametrized dynamical systems in presence of measureme

Hypothesis-and-Refinement Learning of Organic Structures from Multimodal Spectroscopic Data

arXiv:2607.19816v1 Announce Type: cross Abstract: Determining molecular structures from spectroscopic data remains fundamentally challenging because the inverse problem is intrinsically underdetermine

I built an open-source RAG chatbot starter that runs fully locally with Ollama (FastAPI + ChromaDB)

I kept re-wiring the same RAG plumbing on every project, so I turned it into a clean starter and open-sourced it. Upload a PDF, ask questions, and get answers with page-level source citations. It runs

model-releasesr-ollama

I trained a 0.5M model on 1B tokens of Fineweb-edu dataset.

Hi everyone, About a month ago I publish my very first research paper on my neural network architecture called Silia. You can look at the model here: https://huggingface.co/Srijan-Srivastava/Silia-v2

IBoxCLA: Towards Robust Box-supervised Segmentation of Polyp via Improved Box-dice and Contrastive Latent-anchors

arXiv:2310.07248v5 Announce Type: replace Abstract: Box-supervised polyp segmentation attracts increasing attention for its cost-effective potential. Existing solutions often rely on learning-free met

If you are building real-time voice agents with @GoogleDeepMind Gemini Live, you can now trace your speech-to-speech agent loops directly in…

model-releasesharrison-chase--x

If you are building real-time voice agents with @GoogleDeepMind Gemini Live, you can now trace your speech-to-speech agent loops directly in @LangChain! - Speaker callback hooks capture only the exact

Importance-Aware OBS Pruning for Diffusion Models

arXiv:2607.20048v1 Announce Type: new Abstract: We propose importance-aware pruning for diffusion models, a training-free framework that prioritizes preserving parameters critical to semantically sali

In a leaked four-hour investor talk, DeepSeek's Liang Wenfeng says the main US-China gap is compute access, Nvidia's CUDA moat is disintegrating, and more (Fred Gao/Inside China)

Fred Gao / Inside China: In a leaked four-hour investor talk, DeepSeek's Liang Wenfeng says the main US-China gap is compute access, Nvidia's CUDA moat is disintegrating, and more — In a rare four-hou

model-releasestechmeme

In-Context Learning for Wound Classification with Small Multimodal Language Models

arXiv:2607.18819v1 Announce Type: new Abstract: Wound image classification is often treated as a task-specific supervised learning problem, requiring substantial amounts of manually labelled data and

inclusionAI/LLaDA2.2-flash · Hugging Face

LLaDA2.2-flash is an agent-oriented diffusion language model in the LLaDA2 series. By introducing Levenshtein Editing (with DELETE and INSERT control tokens) to diffusion language modeling, it represe

Information Discernment in Large Language Models

arXiv:2607.19355v1 Announce Type: new Abstract: LLMs are increasingly used with external knowledge sources like the internet. Do they weigh information appropriately -- updating more for reliable sour

Interactive Medical-SAM2 GUI: A Napari-based semi-automatic annotation tool for medical images

arXiv:2602.22649v2 Announce Type: replace Abstract: Interactive Medical-SAM2 GUI is an open-source desktop application for semi-automatic annotation of 2D and 3D medical images. Built on the Napari mu

Interpretable Deep Learning Paradigm for Airborne Transient Electromagnetic Inversion

arXiv:2503.22214v2 Announce Type: replace Abstract: The extraction of geoelectric structural information from airborne transient electromagnetic (ATEM) data primarily involves data processing and inve

Introducing the Qwen-Audio-3.0-TTS. Our latest text-to-speech model, in two flavors: • Flash: real-time interaction • Plus: high-quality gen…

Introducing the Qwen-Audio-3.0-TTS. Our latest text-to-speech model, in two flavors: • Flash: real-time interaction • Plus: high-quality generation What's new: • Fine-grained inline tags-steer [whispe

model-releasesqwen--x

It Depends on the Dataset: When a Brain-Encoding Model's Predicted Responses Beat Their Visual Backbone for Video Memorability

arXiv:2607.16292v2 Announce Type: replace Abstract: Brain-encoding foundation models predict fMRI responses to video, audio, and text well enough to win the Algonauts 2025 challenge. We ask whether th

ITPEval: Benchmarking Formal Translation Across Interactive Theorem Provers

arXiv:2607.19407v1 Announce Type: new Abstract: Formal theorem proving has emerged as a frontier challenge for machine learning, yet the ecosystem is fragmented: proofs remain siloed across incompatib

It's Not What You Say, It's How You Say It: Evaluating LLM Responses to Expressions of Belief

model-releasesarxiv-cs-cl

arXiv:2607.18232v2 Announce Type: replace Abstract: Users frequently express their beliefs to large language models (LLMs). In some situations, the LLM should accept these contextual beliefs as true.

JailMeter: An Evidence-Based Evaluation Framework for Jailbreak Attacks on Large Language Models

arXiv:2607.19424v1 Announce Type: cross Abstract: The assessment of jailbreak attacks against large language models currently suffers from inconsistent evaluation criteria and methods, leading to unre

Kimi K3 is coming to Together AI on day zero, July 27. Start building with it the moment it launches, powered by Together AI inference for c…

model-releasestogether-ai--x

Kimi K3 is coming to Together AI on day zero, July 27. Start building with it the moment it launches, powered by Together AI inference for coding, agents, and production workloads. https://www.togethe

KineBench: Benchmarking Embodied World Models via IDM-Free Kinematic Grounding

model-releasesarxiv-cs-ro

arXiv:2607.19876v1 Announce Type: new Abstract: Evaluating the physical consistency of embodied world models(EWMs) is a critical open challenge. While closed-loop evaluation via simulator rollouts off

Kwaipilot/KAT-Coder-V2.5-Dev · Hugging Face

from kwaipilot: Following the release of KAT-Coder-V2.5 in July, we are pleased to release the open-weight version KAT-Coder-V2.5-Dev, an MOE model with a total parameter count of 35B and 3B activated

LAARA: Layer-Aware Adaptive Rank Allocation for Parameter-Efficient Fine-Tuning

arXiv:2607.19391v1 Announce Type: cross Abstract: Low-Rank Adaptation is widely used for parameter-efficient fine-tuning, yet existing methods typically assign the same adapter rank to every transform

Laguna-S-2.1 'thinking forever' loops seem to be a quantization artifact

If you're running Laguna S 2.1 on llama.cpp and hitting thinking loops because it won't close its </think> tags, you might want to look at your quant before you spend too much time tweaking settings.

Language-Specific versus Cross-Lingual Knowledge Graphs for Implicit Aspect Identification in Arabic: A Comparative Study of Reasoning and Adaptation Strategies

arXiv:2607.20056v1 Announce Type: cross Abstract: Aspect-based sentiment analysis (ABSA) in Arabic must recover both explicitly stated aspects and implicit aspects that are never named in the text. Im

Learning Explicit Physical Parameter Control and Benchmarking for Video Generation

arXiv:2607.18924v1 Announce Type: new Abstract: Recent advances in image-to-video generation have improved visual realism, making physically grounded and controllable dynamics an important step toward

Leveraging Offline Supervision for Efficient and Generalizable Reinforcement Learning in Large-Scale Vision-Language-Action Models

arXiv:2607.19399v1 Announce Type: cross Abstract: It is commonly observed that online reinforcement learning (RL) produces better-performing strategies than offline methods across a broad range of per

LISA: Linear-Indexed Sparse Attention for Efficient Long-Context Reasoning

arXiv:2607.19358v1 Announce Type: new Abstract: Recent advances in long chain-of-thought reasoning models such as DeepSeek-R1 have led to increasingly longer inference context lengths under the test-t

LKValues: Aligning Large Language Models with Sri Lankan Societal Values

model-releasesarxiv-cs-cl

arXiv:2607.20410v1 Announce Type: new Abstract: Value alignment of Large Language Models (LLMs) has been shown to be culturally biased toward Western norms. This results in the mishandling of local va

Local Label-Informed Feature Transfer for Generating Ground-Truth Medical Images: A Comparison of GAN- and Diffusion-Based Approaches

arXiv:2607.18882v1 Announce Type: new Abstract: Validating Explainable Artificial Intelligence (XAI) methods in medical imaging requires ground-truth data with known locations of informative features.

Long-Term Sequential Decision Making under Risk

arXiv:2607.19914v1 Announce Type: new Abstract: We study finite-horizon MDP planning under root-based (resolute) risk objectives that apply a rank-dependent functional to the distribution of total ret

LoRFT: Benchmarking Long-Range Vehicle Trajectory Reconstruction from Fixed Highway Cameras

arXiv:2607.19911v1 Announce Type: new Abstract: Long-range vehicle trajectories provide important spatio-temporal evidence for traffic safety analysis, autonomous driving evaluation, and data-driven t

LTX Desktop v1.1.0 is out: local generation on Apple Silicon, a built-in LoRA library, video extend, and more

model-releasesr-stablediffusion

LTX Desktop v1.1.0 just shipped with some big updates. Apple Silicon Macs can generate video locally now, there's a built-in LoRA/IC-LoRA library you can browse and apply from inside the app with per-

MagicPrompt: Ultra-Lightweight Prompt Tuning for Video Generation

arXiv:2607.14595v2 Announce Type: replace Abstract: Large-scale video diffusion models deliver strong generation performance, but full fine-tuning for downstream tasks incurs prohibitive computational

Many still debate open vs closed, and compare cost per token (accounting metric). Better to shift attention to cost per successful task. @se…

model-releasesfireworks-ai--x

Many still debate open vs closed, and compare cost per token (accounting metric). Better to shift attention to cost per successful task. @seldo and the team at @arizeai did so across 2,400 runs. Concl

Marine Engine Fault Dataset: Open-Access Data under Controlled Reference and Fault Scenario Conditions

arXiv:2607.19444v1 Announce Type: new Abstract: Open-access datasets for marine-engine predictive maintenance remain scarce, particularly those from controlled fault experiments with documented operat

Mark Zuckerberg launches a media campaign positioning the company's AI development as an optimistic, pro-human alternative to its competitors' 'dystopian' ideas (Sara Fischer/Axios)

Sara Fischer / Axios: Mark Zuckerberg launches a media campaign positioning the company's AI development as an optimistic, pro-human alternative to its competitors' “dystopian” ideas — Meta CEO Mark Z

model-releasestechmeme