All entries

Resample or Reroute? Budget-Aware Test-Time Model Selection for Large Language Models

model-releasesarxiv-cs-lg

arXiv:2607.08665v1 Announce Type: new Abstract: Routing among large language models (LLMs) trades response quality against serving cost, motivated by the reported gap between deployed routers and a pe

Resolving Predictive Multiplicity for the Rashomon Set

DGX agent

arXiv:2601.09071v2 Announce Type: replace Abstract: The existence of multiple, equally accurate models for a given predictive task leads to predictive multiplicity, where a Rashomon set of models achi

local-aiarxiv-cs-lg

10 Jul 2026

RetailBench: Evaluating Long-Horizon Autonomous Decision-Making and Strategy Stability of LLM Agents in Realistic Retail Environments

model-releasesarxiv-cs-ai

arXiv:2603.16453v3 Announce Type: replace Abstract: Large language model (LLM) agents have made rapid progress on short-horizon, well-scoped tasks, yet their ability to sustain coherent decisions in d

Rethinking LLM-as-a-Judge: Representation-as-a-Judge with Small Language Models via Semantic Capacity Asymmetry

arXiv:2601.22588v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are widely used as reference-free evaluators via prompting, but this 'LLM-as-a-Judge' paradigm is costly, opaque,

Local Ai

Rethinking Small VLM Quantization: From Component-Wise Analysis to Hardware-Aware Edge Deployment

arXiv:2607.08029v1 Announce Type: new Abstract: The emergence of vision language models with fewer than 3 billion parameters has accelerated the implementation of on-device multimodal intelligence. Ho

local-aiarxiv-cs-lg

Retrieval of Scientific and Technological Resources for Experts and Scholars

arXiv:2204.06142v2 Announce Type: replace-cross Abstract: Institutions of higher learning, research institutes and other scientific research units have abundant scientific and technological resources

Revisiting One-Zero and Two-Zero Neutrino Mass Textures in Light of Recent Oscillation and Cosmological Data

arXiv:2607.08384v1 Announce Type: cross Abstract: We revisit one-zero and two-zero textures of the neutrino mass matrix under current experimental and cosmological constraints. We identify the phenome

Local Ai

RhyMix: A Lightweight Adaptive Multi-Rhythm Network for Long-Term Time Series Forecasting

arXiv:2607.08234v1 Announce Type: cross Abstract: Real-world time series exhibit complex dynamics characterized by multiple simultaneous temporal patterns: short-term fluctuations, periodic seasonal c

local-aiarxiv-cs-ai

Applications

Robust Bayesian Decision Making under Adversarial Uncertainty

arXiv:2607.08590v1 Announce Type: new Abstract: Scientific experiments are often designed to maximize information gain, yet in many applications the primary objective is to support reliable downstream

applicationsarxiv-cs-lg

Robust Weighted Triangulation of Causal Effects Under Model Uncertainty

arXiv:2603.01119v2 Announce Type: replace-cross Abstract: A fundamental challenge in causal inference with observational data is correct specification of a causal model. When there is model uncertaint

Robustness Quantification for Discriminative Models: a New Robustness Metric and its Application to Dynamic Classifier Selection

arXiv:2603.23318v2 Announce Type: replace Abstract: Among the different possible strategies for evaluating the reliability of individual predictions of classifiers, robustness quantification stands ou

Rocket Report: 'Panic' over Transporter availability; Isar to launch from Canada

Industry concerns about SpaceX's Transporter rideshare program availability have reached 'panic' levels, with reports that SpaceX is not accepting new Transporter reservations beyond late 2028 or earl

industryars-technica

Local Ai

Run Transcribe Arabic locally on your MacBook thanks to @Prince_Canuma and @lllucas 🚀 Keep track of meetings, dictate voice notes, and more…

Cohere has enabled local Arabic speech-to-text transcription on MacBooks through contributions from Prince_Canuma and lllucas, allowing users to transcribe meetings, voice notes, and other audio witho

local-aicohere--x

Safe Flow Q-Learning: Offline Safe Reinforcement Learning with Reachability-Based Flow Policies

arXiv:2603.15136v2 Announce Type: replace-cross Abstract: Offline safe reinforcement learning (RL) seeks reward-maximizing policies from static datasets under strict safety constraints. Existing metho

safetyarxiv-cs-ai

SAGA: Stable Acceleration Guidance for Autoregressive Video Generation

arXiv:2607.08020v1 Announce Type: new Abstract: Autoregressive video diffusion enables efficient streaming and long-horizon video generation, but repeatedly reusing generated latents as causal context

researcharxiv-cs-cv

Tutorials

Sam Altman should be in prison. But if we can’t have that, I’ll settle for him being a broke pariah.

Sam Altman should be in prison. But if we can’t have that, I’ll settle for him being a broke pariah. OpenAI hardware chief Tang Tan allegedly helped coach recruits on how to evade Apple’s data securit

tutorialsgary-marcus--x

SAM-MT: Real-Time Interactive Multi-Target Video Segmentation

arXiv:2607.08688v1 Announce Type: new Abstract: Modern Video Object Segmentation (VOS) involves tracking and segmenting user-specified targets. While recent approaches have achieved remarkable perform

researcharxiv-cs-cv

SASGeo: Stability-Aware Semantic Map Localization for GNSS-Denied UAVs -- A Framework and Synthetic Proof of Concept

arXiv:2607.07737v1 Announce Type: cross Abstract: GNSS-denied unmanned aerial vehicles require occasional absolute position fixes to bound the drift of visual-inertial odometry. Cross-view image retri

safetyarxiv-cs-cv

Scalable and Culturally Specific Stereotype Dataset Construction via Human-LLM Collaboration

arXiv:2607.07895v1 Announce Type: new Abstract: Research on stereotypes in large language models (LLMs) has largely focused on English-speaking contexts, due to the lack of datasets in other languages

safetyarxiv-cs-cl

Scalable and Trustworthy Earth Observation Foundation Models

model-releasesarxiv-cs-lg

arXiv:2607.07758v1 Announce Type: new Abstract: Foundation models (FMs) have transformed machine learning from isolated task-specific model development toward general-purpose models pretrained on broa

Scaling agentic workflows with native case management in Amazon Quick Automate

In this post, we show you how to combine case management with agentic automation capabilities in Quick Automate. We introduce case management and explore the lifecycle of cases in an agentic workflow

agentsaws-ml-blog

Score Accuracy Along the Forward Diffusion Does Not Certify Numerical Stability in Diffusion Sampling

arXiv:2607.08757v1 Announce Type: cross Abstract: Score matching controls average error under the forward marginals, but a discretized reverse-time sampler evaluates the learned score along its own tr

Search-based Testing of Vision Language Models for In-Car Scene Understanding

arXiv:2607.02300v2 Announce Type: replace Abstract: In the automotive domain, in-car scene understanding (ISU) enables the detection of safety-critical events, such as driver distraction, and supports

safetyarxiv-cs-cv

Secure Decentralized Federated Learning via Gossip and Virtual Voting

model-releasesarxiv-cs-lg

arXiv:2607.08651v1 Announce Type: new Abstract: Decentralized federated learning (DFL) removes the central server by letting nodes exchange model updates through peer-to-peer gossip, but existing goss

Securing Autonomous Vehicle Systems via Twin-Aware Federated Reinforcement Learning

arXiv:2607.08137v1 Announce Type: cross Abstract: Federated reinforcement learning (FRL) is crucial for enabling collaborative learning across multiple agents without sharing raw data, thereby enhanci

safetyarxiv-cs-lg

Applications

See everything new in Cursor, including new cloud agent hooks: http://cursor.com/changelog/side-chat

Cursor has released updates featuring new cloud agent hooks and side-chat functionality, expanding its AI-assisted development capabilities. The changelog details recent features and improvements to t

agentscursor--x

SeFA-Policy: Fast and Accurate Visuomotor Policy Learning with Selective Flow Alignment

arXiv:2511.08583v2 Announce Type: replace-cross Abstract: Developing efficient and accurate visuomotor policies poses a central challenge in robotic imitation learning. While recent rectified flow app

safetyarxiv-cs-lg

Selective Left-Shift: Turning Test-Time Compute and Difficulty-based Curation into Training Data for Low-Resource Code Generation

arXiv:2607.07748v1 Announce Type: new Abstract: Large Language Models achieve strong code generation for high resource languages like Python and Java but suffer sharp performance drops on Low-Resource

Self-Adaptive Anomaly Detection with Reinforcement Learning and Human Feedback in Connected Vehicles

arXiv:2607.08373v1 Announce Type: cross Abstract: Connected vehicles are autonomous cyber-physical systems whose behavior must be continuously monitored during operation to detect deviations from norm

Self-EvolveRec: Self-Evolving Recommender Systems with LLM-based Directional Feedback

arXiv:2602.12612v2 Announce Type: replace-cross Abstract: Traditional methods for automating recommender system design, such as Neural Architecture Search (NAS), are often constrained by a fixed searc

Semantic Representation Learning of Scientific Literature based on Adaptive Feature and Graph Neural Network

arXiv:2311.00296v2 Announce Type: replace Abstract: Because most scientific literature data are unlabeled, semantic representation learning based on unsupervised graphs has become crucial. To enrich s

researcharxiv-cs-cl

SHAP-Weighted Cross-Modal Expert Fusion for Emotion and Sentiment Recognition: Evidence and Limits

arXiv:2607.08573v1 Announce Type: new Abstract: Multimodal emotion and sentiment recognition is commonly addressed by early fusion, which concatenates modalities before classification, or late fusion,

Shift & Drift: A Zero-Shot Benchmark for Generalizable and Robust Autonomous Driving Motion Planning

model-releasesarxiv-cs-ai

arXiv:2607.07844v1 Announce Type: cross Abstract: While closed-loop motion planners trained on large-scale, object-level datasets, e.g., nuPlan, demonstrate strong in-distribution (ID) performance, th

SHIFT: Survival Prediction from Incomplete and Heterogeneous Genomic Data

arXiv:2607.07725v1 Announce Type: cross Abstract: Genomic prediction models often fail to transfer across institutions because sequencing panels differ across sites, creating structural feature missin

Sierra isn't the first to build this - Ramp, Stripe, CoinBase also have If you want an open source version - check out OpenSWE: https://gith…

Sierra isn't the first to build this - Ramp, Stripe, CoinBase also have If you want an open source version - check out OpenSWE: https://github.com/langchain-ai/open-swe We use it internally (mostly fo

agentsharrison-chase--x

Sign Identifiability of Causal Effects in Stationary Stochastic Dynamical Systems

arXiv:2603.08311v2 Announce Type: replace-cross Abstract: We study identifiability in continuous-time linear stationary stochastic differential equations with a known causal structure. Unlike existing

SimRPD: Optimizing Recruitment Proactive Dialogue Agents through Simulator-Based Data Evaluation and Selection

arXiv:2601.02871v3 Announce Type: replace Abstract: Task-oriented proactive dialogue agents play a pivotal role in recruitment, particularly for steering conversations towards specific business outcom

Simulator Ensembles for Trustworthy Autonomous Driving Systems Testing

arXiv:2503.08936v3 Announce Type: replace-cross Abstract: Scenario-based testing with driving simulators is extensively used to identify failing conditions of automated driving assistance systems (ADA

SK Hynix CEO Kwak Noh-Jung says the memory industry is heading for its worst-ever supply shortage in 2027 and demand will outstrip supply beyond 2030 (Reuters)

Reuters: SK Hynix CEO Kwak Noh-Jung says the memory industry is heading for its worst-ever supply shortage in 2027 and demand will outstrip supply beyond 2030 — SK Hynix (000660.KS) Chief Executive Kw

industrytechmeme

SK Hynix opens up 14% at 170 after raising 26.5B in the largest ever US market debut by a foreign company (Kif Leswing/CNBC)

Kif Leswing / CNBC: SK Hynix opens up 14% at 170 after raising 26.5B in the largest ever US market debut by a foreign company — SK Hynix opened at $170 per share on the Nasdaq on Friday, rising about

industrytechmeme

Applications

SkelGen4D: Weakly-Supervised Skeleton-Based 4D Generation for Text-Driven Mesh Animation

arXiv:2607.08246v1 Announce Type: new Abstract: We study 4D generation to synthesize temporally coherent sequences of 3D geometry for animation and content creation. In contrast to existing SDS-based

applicationsarxiv-cs-cv

SkillPlug: Unsupervised Skill Mining for Few-Shot Adaptation in Robotic Manipulation

arXiv:2607.08354v1 Announce Type: new Abstract: Learning transferable visuomotor imitation policies that generalize across diverse manipulation tasks and adapt rapidly to new tasks from only a handful

safetyarxiv-cs-ro

Hardware

SLORR: Simple and Efficient In-Training Low-Rank Regularization

arXiv:2607.08754v1 Announce Type: cross Abstract: Low-rank factorization is widely used to compress neural networks, but modern models are often not naturally amenable to aggressive factorization with

hardwarearxiv-cs-ai

SMetric: Rethink LLM Scheduling for Serving Agents with Balanced Session-centric Scheduling

arXiv:2607.08565v1 Announce Type: cross Abstract: LLM scheduling is critical to serving, yet it remains unclear how well existing designs fit agentic serving--with LLM requests issued by agents instea

Soft Robotic Exogloves for Dexterous Mobility -- Towards Personalized Rehabilitation

arXiv:2607.07968v1 Announce Type: new Abstract: Soft robotic exogloves can provide hand rehabilitation and assistance. Fitting these gloves often relies on standardized measurements not tailored to th

safetyarxiv-cs-ro

SolarChain-Eval: A Physics-Constrained Benchmark for Trustworthy Economic Agents in Decentralized Energy Markets

model-releasesarxiv-cs-ai

arXiv:2607.08681v1 Announce Type: new Abstract: As agentic AI systems are increasingly applied to cyber-physical environments, their evaluation requires assessment of both task performance and trustwo

Source: Greg Brockman will continue to oversee OpenAI's products as the company doesn't plan to hire anyone to replace Fidji Simo after she stepped down (CNBC)

CNBC: Source: Greg Brockman will continue to oversee OpenAI's products as the company doesn't plan to hire anyone to replace Fidji Simo after she stepped down — There's a new second-in-command at Open

industrytechmeme