Search: “model-releases”

CMT-RAG: Complementary Memory Traces for Multi-turn Multi-hop RAG

arXiv:2607.26470v1 Announce Type: new Abstract: Multi-turn information-seeking conversations require both multi-hop reasoning and long-range dependency tracking across turns. However, existing RAG sys

Model Releases

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

DGX agent

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.

model-releasesarxiv-cs-lg

30 Jul 2026

ComfyUI Face Swap Tutorial: Fast, Clean Results VFX artist Doug Hogan walks through a fully automated face swap workflow built inside ComfyU…

ComfyUI Face Swap Tutorial: Fast, Clean Results VFX artist Doug Hogan walks through a fully automated face swap workflow built inside ComfyUI - combining Florence 2, SAM2, and WAN Video into a single

model-releasescomfyui--x

Consistent with what I found with Qwen3.6 a while back: Claude Code uses 2-3x as many tokens than (many) other harnesses at similar success …

model-releasessebastian-raschka--x

Consistent with what I found with Qwen3.6 a while back: Claude Code uses 2-3x as many tokens than (many) other harnesses at similar success rate. - Unoptimized? - Buggy? - Deliberate (coz that helps i

Cost-Sensitive Conformal Prediction and Human-in-the-Loop Abstention for Imbalanced High-Stakes Decision Support: A Multi-Domain Benchmark

arXiv:2607.27143v1 Announce Type: new Abstract: High-stakes decision systems in credit scoring, fraud detection, healthcare, and industrial safety require reliable uncertainty quantification under sev

Credit Cards, Confusion, Computation, and Consequences: What Can We Uncover About Language Model Reasoning?

arXiv:2607.26952v1 Announce Type: new Abstract: We introduce CreditCardQA, the first financial literacy benchmark for numerical reasoning derived from real credit card agreements. The dataset contains

Crossing-Free Probabilistic K-Line Forecasts Without Retraining

arXiv:2607.26792v1 Announce Type: cross Abstract: Probabilistic K-line forecasting describes uncertainty in four complementary prices, namely open--high--low--close (OHLC). However, it introduces two

Decoupled Visual Processing: Efficient Multimodal Adaptation via Modality-Specific Transformer Substitution

arXiv:2607.26596v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have demonstrated remarkable capabilities by integrating visual and textual understanding within a unified tran

Defending Against Backdoor Attacks via Alignment Checking in Model-Contrastive Federated Learning

arXiv:2607.26933v1 Announce Type: cross Abstract: Federated Learning (FL) is vulnerable to backdoor attacks because of its distributed nature in edge computing scenarios. Existing defense methods show

DenseOn with the LateOn: Fully Open Dense and Late-Interaction Models for Multilingual, Long-Context, and Code Search

arXiv:2607.27178v1 Announce Type: new Abstract: State-of-the-art retrieval models increasingly rely on closed training data, creating a reproducibility gap. We present an open end-to-end recipe for tr

Diagnosing Fine-Grained Inconsistency Classification in Financial Disclosure Text

arXiv:2607.26368v1 Announce Type: new Abstract: Financial disclosures contain numerical claims, temporal statements, entity references, policy commitments, and risk descriptions that may conflict in q

DialectLLM: A Dialect-Aware Dialog[ue] Generation Framework Beyond Standard American English

arXiv:2601.22888v4 Announce Type: replace Abstract: More than 80% of the 1.6B English speakers do not use Standard American English (SAE), yet LLMs often fail to correctly identify non-SAE dialects an

Does MTP head get loaded in VRAM by default?

model-releasesr-localllama

I ran into a doubt when using the following command. It seems that the System RAM usage keeps increasing even though there is >10GB of space left in VRAM while using the MTP mode. Does the MTP head lo

EgoSafe: A First-Person Mobile-Captured Benchmark for Visual Safety Understanding

arXiv:2607.26518v1 Announce Type: new Abstract: Reliable visual safety understanding in real-world scenarios demands more than just object recognition; it requires causal reasoning under epistemic unc

Enhancing Automated Machine Learning via Homogeneous Train-Test Splitting Methods

arXiv:2607.26625v1 Announce Type: new Abstract: Accurate model evaluation in machine learning depends critically on how datasets are split into training and testing subsets. Standard random splitting

Enhancing Generative Information Extraction with Two-step Validation: A Product Attribute Use Case

arXiv:2607.26780v1 Announce Type: new Abstract: The ability of large language models (LLMs) to process and generate text has introduced potential for applications in information extraction (IE). While

Equivariant Eikonal Neural Networks: Grid-Free, Scalable Travel-Time Prediction on Homogeneous Spaces

arXiv:2505.16035v3 Announce Type: replace Abstract: We introduce Equivariant Neural Eikonal Solvers, a novel framework that integrates Equivariant Neural Fields (ENFs) with Neural Eikonal Solvers. Our

Evaluating Prompt Scope and Demonstration Similarity in Local LLM Machine Translation

arXiv:2607.26286v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used as general-purpose translation systems, but their behavior is usually evaluated under a single prompt

EvoPINN: Agentic Discovery of Executable Algorithms for Physics-Informed Neural Networks

arXiv:2607.26490v1 Announce Type: cross Abstract: Physics-informed neural networks (PINNs) have emerged as a powerful paradigm for solving partial differential equations (PDEs), yet their performance

exttt{AMEND++}: Benchmarking Eligibility Criteria Amendments in Clinical Trials

arXiv:2601.06300v2 Announce Type: replace Abstract: Clinical trial amendments frequently introduce delays, increased costs, and administrative burden, with eligibility criteria being the most commonly

FAS-R1: A Unified Multi-Task MLLM for Reasoning Face Anti-Spoofing

arXiv:2607.26432v1 Announce Type: new Abstract: Face anti-spoofing (FAS) is increasingly expected to provide not only bona fide/spoof decisions, but also attack semantics and image-grounded evidence f

FedTopo: Relation-Level Topology Sharing for Model-Heterogeneous Federated Learning

arXiv:2607.26801v1 Announce Type: new Abstract: Federated learning (FL) enables collaborative learning over decentralized data silos without centralizing raw data. However, heterogeneous local archite

FedWeave: Rethinking the Unit of Specialization in Heterogeneous Federated MoE-LoRA

arXiv:2607.26618v1 Announce Type: cross Abstract: Federated PEFT enables LLMs to collaboratively adapt to decentralized private data without sharing raw examples. However, task heterogeneity across cl

Financial Volatility and Risk Forecasting Incorporating a Larger Number of Realized Measures

arXiv:2411.17136v2 Announce Type: replace-cross Abstract: Realised volatility has become increasingly prominent in volatility forecasting due to its ability to capture intraday price fluctuations. Wit

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.

For decades, we’ve dreamed of robots that can seamlessly step into our world and lend a hand. Today, we take a major stride toward making th…

model-releasesgoogle-ai--x

For decades, we’ve dreamed of robots that can seamlessly step into our world and lend a hand. Today, we take a major stride toward making that dream a reality: Introducing Gemini Robotics 2 from @Goog

ForgetBench: Benchmarking Forgetting Dynamics of Long-Term Parametric Memory in Language Models

arXiv:2607.26455v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated strong capabilities in knowledge acquisition and reasoning, yet their ability to retain previously acquir

Foundation Models for Face Presentation Attack Detection: A Unified Linear-Probing Benchmark

arXiv:2607.26993v1 Announce Type: new Abstract: Face presentation attack detection (PAD) remains challenging under cross-dataset evaluation, where domain shift degrades models trained on a single data

From Tokens to Watt-hours: Analytical Energy Estimation for LLM Inference on Modern GPUs

arXiv:2607.26571v1 Announce Type: new Abstract: The operational energy consumption of large language model (LLM) inference is becoming an increasingly important component of the environmental footprin

Gated Adaptation for Continual Learning in Human Activity Recognition

arXiv:2603.10046v2 Announce Type: replace Abstract: Wearable sensors in Internet of Things (IoT) ecosystems increasingly support applications such as remote health monitoring, elderly care, and smart

Gemini Robotics ER 2: powering robotics with video understanding, task orchestration, and multi-robot collaboration

model-releasesgoogle-deepmind

Gemini Robotics ER 2 helps robots reason, collaborate, and solve real-world tasks. It represents a step change in video understanding, tool orchestration, and multi-robot collaboration for robotic app

GEqTrain: A Configuration-Driven Framework for Retargeting Equivariant Graph Neural Networks Across 3D Scientific Tasks

arXiv:2607.19083v2 Announce Type: replace Abstract: Equivariant graph neural networks provide a powerful modeling language for three-dimensional scientific data, but their reuse is often limited by im

goblin-level blog post

model-releasessam-altman--x

goblin-level blog post Turns out GPT-5.6 Sol is actually SoTA on ARC-AGI-3. Just took two setting changes. You just have to allow it to reason and work over multiple context windows with the help of o

good job little bro

model-releasessam-altman--x

good job little bro After deployment, we applied GPT-5.6 Sol to advance the frontier of efficiency by making itself more efficient to run. The results: - 20% lower serving costs from production GPU ke

Google DeepMind debuts Gemini Robotics 2 model series for humanoid robots

model-releasessiliconangle

Alphabet Inc.’s artificial intelligence research lab today debuted a family of models optimized to power humanoid robots. Google DeepMind says that the Gemini Robotics 2 series enables multiple autono

Google DeepMind’s new AI model can control a robot’s entire body

model-releasesthe-verge-ai

Google DeepMind says the latest version of its Gemini Robotics AI model can 'control entire humanoid robots.' While the previous model focused on controlling a humanoid robot's upper body, Gemini Robo

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

GPT-5.6 found optimizations that 'reduced end-to-end serving costs by 20%' for OpenAI to serve that model Presumably that's billions of doll…

model-releasessimon-willison--x

GPT-5.6 found optimizations that 'reduced end-to-end serving costs by 20%' for OpenAI to serve that model Presumably that's billions of dollars a month in savings at this point? Codex analysed product

GPT-Red: Automated Red Teaming via Self-Play at Scale

arXiv:2607.26115v1 Announce Type: cross Abstract: We introduce extbf{GPT-Red}, an automated red-teaming agent that is trained to discover novel prompt injection attacks against frontier LLMs. The goal

Hearsay: Vision-Language Medical Diagnoses Without an Image

arXiv:2607.26886v1 Announce Type: cross Abstract: When asked to describe a medical image that was never attached, frontier vision-language models do not abstain: they confabulate a diagnosis. We show

HoF-Bench: Rediscovering Real AI-Discovered CVEs Without Frontier Models

arXiv:2607.27030v1 Announce Type: cross Abstract: LLM-based analyzers have begun finding real vulnerabilities in mature open-source projects: AISLE's analyzer is credited with more than 280 CVEs acros

How close are we to local llama robotics for consumer price point?

model-releasesr-localllama

I'm guessing 3 years, what do you think? In other words: many of us will be able to afford a general purpose robot in 3 years to experiment with in the home. Cost roughly $5k? Probably small size, but

How Kimi K3 Engineered Its Way to the Frontier [R]

model-releasesr-machinelearning

Kimi K3 by Moonshot reached the frontier as an open-weight model. Artificial Analysis ranks it fourth of 580 models, behind only Claude Opus 5, Fable 5, and GPT-5.6 Sol. Moonshot released more than th

How to uninstall Ollama Claude code

pretty simple I did ollama launch claude, found out its slow asf, wanted to delete It and Idk how I have no idra if its the same as normal Claude Code uninstall or if it's a Little bit of a different

model-releasesr-ollama

HumanCLAW: Can Vision-Language Models Act Through a Body?

arXiv:2607.27180v1 Announce Type: new Abstract: Evaluating whether a vision-language model (VLM) can act through a physical body is challenging. The outcome of an action couples the VLM's decision wit

ICDAR 2026 Competition on Information Extraction from Atomic Layer Deposition/Etching (ALD/E) Scientific Figures

arXiv:2607.26848v1 Announce Type: new Abstract: Scientific figure comprehension and reasoning using multimodal AI requires integrating visual perception with domain-specific reasoning to extract meani

Identifying Implicit Bias in LLM-based Chat AI Toward People with Intellectual Disabilities

arXiv:2607.26062v1 Announce Type: cross Abstract: Background: This work investigates the presence of implicit bias in Large Language Model (LLM)-based chat AI models directed toward people with intell

I'm actually fairly bearish on frontier lab valuations. I've never seen the reasons articulated to my satisfaction, so before I go to sleep,…

model-releasesgary-marcus--x

I'm actually fairly bearish on frontier lab valuations. I've never seen the reasons articulated to my satisfaction, so before I go to sleep, I wanted to quickly jot down my thinking here. The basic is