All entries

RaBitQCache: Rotated Binary Quantization for KVCache in Long Context LLM Inference

arXiv:2606.31519v1 Announce Type: cross Abstract: Long-context Large Language Model inference is severely bottlenecked by the massive Key-Value (KV) cache, yet existing sparse attention methods often

researcharxiv-cs-cl

Radial Suppression Accelerates Algorithmic Generalization: A Geometric Analysis of Delayed Generalization

DGX agent

arXiv:2606.32000v1 Announce Type: cross Abstract: Why do neural networks memorize algorithmic training data long before they generalize? We present a geometric case study demonstrating that, on tasks

model-releasesarxiv-cs-ai

1 Jul 2026

Applications

RAISE: LLM-based Automated Heuristic Design with Robust Adversary Instance Search

arXiv:2606.31801v1 Announce Type: new Abstract: Automated Heuristic Design (AHD) with Large Language Models (LLMs) has shown remarkable progress in discovering high-quality heuristics. However, existi

applicationsarxiv-cs-ai

Hardware

Raja Koduri’s Oxmiq Labs raises $35M to lower the design cost of custom AI silicon

Artificial intelligence chipmaking startup Oxmiq Labs Inc. says it wants to become the next Arm Holdings Plc. after raising 35 million in an early-stage A funding, bringing its total amount raised to

hardwaresiliconangle

Random Reshuffling Dominates Stochastic Gradient Descent

arXiv:2606.32005v1 Announce Type: cross Abstract: Stochastic Gradient Descent (extsf{SGD}) is one of the most classical optimization algorithms with favorable theoretical guarantees, yet the practical

researcharxiv-cs-lg

RASR: Retrieval-Augmented Semantic Reasoning for Fake News Video Detection

arXiv:2604.06687v2 Announce Type: replace Abstract: Multimodal fake news video detection is a crucial research direction for maintaining the credibility of online information. Existing studies primari

researcharxiv-cs-cv

Applications

RCL-Mamba: A Dual-domain State Space Model for Measurement-oriented Image Restoration in Rotational Sparse-View Scanning Computed Laminography

arXiv:2606.31353v1 Announce Type: new Abstract: Rotational Scanning Computed Laminography (RCL) is widely utilized for the Non-Destructive Testing(NDT) of large planar components. However, to facilita

applicationsarxiv-cs-cv

RCT: A Robot-Collected Touch-Vision-Language Dataset for Tactile Generalization

arXiv:2606.31694v1 Announce Type: cross Abstract: For robots manipulating open-world objects, tactile representations must generalize to unseen materials. We introduce RCT (Robotic Contact Tactile), a

researcharxiv-cs-ai

ReactionAtlas: Ab origine exploration of chemical reaction networks with machine learning

arXiv:2606.30778v1 Announce Type: new Abstract: Mapping a chemical reaction network, the graph of minima and transition states (TS) and the elementary reactions connecting them, is the natural languag

researcharxiv-cs-lg

Tools

Read about our Series C in the New York Times: http://shorturl.at/SooOP

Together AI announced their Series C funding round, which was covered in a reporting piece by the New York Times. The announcement was shared via their official X (formerly Twitter) account, linking t

toolstogether-ai--x

Tools

Read the blog: https://www.together.ai/blog/icml-2026 See us at ICML: https://www.together.ai/icml-2026

Together AI is announcing their participation in ICML 2026 (International Conference on Machine Learning) and inviting the community to visit them at the conference. The announcement likely includes d

toolstogether-ai--x

Agents

Real-Time Source-Free Object Detection

arXiv:2606.31834v1 Announce Type: cross Abstract: Real-world detectors for autonomous driving, surveillance, and robotics must handle domain-shifts under strict latency and memory constraints, yet exi

agentsarxiv-cs-ai

Really confused by all the excitement I see in my timeline for a nerfed model. Never seen anything like it. So many will end up very disappo…

Really confused by all the excitement I see in my timeline for a nerfed model. Never seen anything like it. So many will end up very disappointed. Time to rethink how to build around frontier and open

model-releasesdair-ai--x

Agents

Reasoning-aware Speculative Decoding for Efficient Vision-Language-Action Models in Autonomous Driving

arXiv:2606.31160v1 Announce Type: new Abstract: Modern Vision-Language-Action (VLA) planners for autonomous driving emit a chain-of-causation (CoC) reasoning step before producing a trajectory. The re

agentsarxiv-cs-cv

Local Ai

Reasoning in machine vision by learning fast and slow thinking

arXiv:2506.22075v2 Announce Type: replace Abstract: Reasoning is a hallmark of human intelligence, enabling adaptive decision-making in complex unfamiliar scenarios. In contrast, machine intelligence

local-aiarxiv-cs-cv

REDI: Corpus Aware Patch Ranking for DINOv3 Token Reduction

arXiv:2606.31676v1 Announce Type: new Abstract: Most token reduction methods for Vision Transformers seek favorable tradeoffs between accuracy and efficiency by pruning, merging, or pooling patch toke

researcharxiv-cs-cv

Reference-Based Prosody and Rhythm Evaluation for Spoken Dialogue Systems

arXiv:2606.31055v1 Announce Type: new Abstract: Speech-to-speech (S2S) AI agents are advancing rapidly, yet evaluation lacks interpretable speech-native measures for conversational prosody and rhythm.

researcharxiv-cs-cl

Reference-Free Image Quality Assessment for Virtual Try-On via Human Feedback

arXiv:2603.13057v2 Announce Type: replace Abstract: As virtual try-on (VTON) systems become increasingly important in fashion e-commerce, there is a growing need for reliable reference-free evaluation

Tutorials

Region-Aware Multimodal Large Language Model via SlowFast Tokenization and Pseudo-Mask Guidance for 3D CT Report Generation

arXiv:2506.23102v2 Announce Type: replace-cross Abstract: Current CT report generation frameworks predominantly rely on global feature representations, often failing to capture region-specific details

tutorialsarxiv-cs-cv

Applications

Registering the 4D Millimeter Wave Radar Point Clouds Via Generalized Method of Moments

arXiv:2508.02187v3 Announce Type: replace-cross Abstract: 4D millimeter wave radars (4D radars) are new emerging sensors that provide point clouds of objects with both position and radial velocity mea

applicationsarxiv-cs-cv

ReGRPO: Reflection-Augmented Policy Optimization for Tool-Using Agents

arXiv:2606.31392v1 Announce Type: new Abstract: Tool-augmented vision-language models (VLMs) can solve multimodal, multi-step tasks by calling external tools, yet they remain fragile in practice. Exis

Reinforcement Learning-Based Control for an Inline Skating Humanoid Robot

arXiv:2606.31807v1 Announce Type: new Abstract: As humanoid robots become increasingly dynamic, coupling them with reinforcement learning offers a promising approach to solving the complex, underactua

safetyarxiv-cs-ro

Reinforcement Learning with Metacognitive Feedback Elicits Faithful Uncertainty Expression in LLMs

arXiv:2606.32032v1 Announce Type: cross Abstract: Metacognition is a critical component of intelligence that describes the ability to monitor and regulate one's own cognitive processes. Yet LLMs exhib

Relational and Sequential Conformal Inference for Energy Time Series over Graphs via Foundation Models

arXiv:2606.31804v1 Announce Type: new Abstract: Accurate energy demand forecasting is essential for the reliable operation and planning of modern sustainable energy systems. Spatial-temporal graph neu

safetyarxiv-cs-lg

REMSA: Foundation Model Selection for Remote Sensing via a Constraint-Aware Agent

model-releasesarxiv-cs-ai

arXiv:2511.17442v3 Announce Type: replace-cross Abstract: Foundation Models (FMs) are increasingly integrated into remote sensing (RS) pipelines. These models include unimodal vision encoders and mult

Industry

Report: SpaceX showed investors an AI device before IPO; Musk denies it

Space Exploration Technologies Corp. showed investors and other stakeholders an early prototype of a handheld artificial intelligence device ahead of its planned initial public offering, the Wall Stre

industrysiliconangle

Reselling “excess AI processing capacity”: first SPCX, now META. In a rational world these moves would be seen as signs that we have *alre…

Reselling “excess AI processing capacity”: first SPCX, now META. In a rational world these moves would be seen as signs that we have *already* started to overbuild. Boom. $META is developing a cloud s

safetygary-marcus--x

Tools

Resend joins the Vercel Marketplace

Resend, an email API platform, has been integrated into the Vercel Marketplace, enabling developers to easily add email capabilities to their Vercel-deployed applications. This integration allows deve

toolsvercel-blog

RESOLVE: A Multi-Resolution and Multi-Modal Dataset for Roadside Cooperative Perception

arXiv:2606.31895v1 Announce Type: new Abstract: LiDAR has increasingly been integrated into traffic cameras to expand coverage and mitigate occlusion in roadside cooperative perception. However, how u

Resolving superposition in AI for interpretability and cross-modal alignment in patient-neuronal images

arXiv:2606.31394v1 Announce Type: cross Abstract: Artificial intelligence is transforming our capability to solve biological challenges. In dimensionality bottleneck regimes exacerbated by high-dimens

Rethinking Foundation Model Collaboration: Enhancing Specialized Models through Proxy Task Reasoning

arXiv:2606.31157v1 Announce Type: new Abstract: Foundation models are increasingly integrated into embodied intelligence systems, but directly assigning them structured prediction tasks requires preci

researcharxiv-cs-cv

Rethinking Garment Conditioning in Diffusion-based Virtual Try-On: Decouple, Don't Denoise

arXiv:2511.18775v2 Announce Type: replace-cross Abstract: Virtual Try-On (VTON) synthesizes realistic images of a person wearing a target garment, with broad applications in e-commerce and fashion. Di

researcharxiv-cs-ai

Rethinking On-policy Optimization for Query Augmentation

arXiv:2510.17139v3 Announce Type: replace Abstract: Recent advances in large language models (LLMs) have led to a surge of interest in query augmentation for information retrieval (IR). Two main appro

safetyarxiv-cs-cl

Rethinking the Role of Feature Engineering and Learning Strategies in Few-Shot Hidden Emotion Recognition

arXiv:2606.31249v1 Announce Type: new Abstract: In this paper, we present the solution developed by our team, XInsight Lab, which achieved first place in Track 3 of the 4th EI-MIGA-IJCAI Challenge wit

Revealing Safety-Critical Scenarios for UTM via Transformer

arXiv:2606.31114v1 Announce Type: new Abstract: Unmanned Traffic Management (UTM) systems are cloud-based platforms designed to manage and coordinate multiple aerial vehicles remotely. UTM systems are

Review Residuals: Update-Conditioned Residual Gating for Transformers

model-releasesarxiv-cs-cl

arXiv:2606.31859v1 Announce Type: cross Abstract: Residual connections add every sublayer's proposed update with a fixed coefficient of one; the network never evaluates whether an update is reliable b

Revising RVL-CDIP: Quantifying Errors and Test-Train Overlap

model-releasesarxiv-cs-cl

arXiv:2606.31446v1 Announce Type: new Abstract: RVL-CDIP is a popular dataset for benchmarking document classifiers. However, the dataset contains ample amounts of label errors as well as non-trivial

Revisiting Audio-language Pretraining for Learning General-purpose Audio Representation

arXiv:2511.16757v2 Announce Type: replace-cross Abstract: Audio-language pretraining (ALP) holds promise for learning general-purpose audio representation, yet remains underexplored. Crucially, there

researcharxiv-cs-ai

Revisiting Parameter Redundancy in Vision-Language-Action Models: Insights from VLM-to-VLA Adaptation

model-releasesarxiv-cs-ro

arXiv:2606.31382v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have made significant strides in embodied intelligence by integrating the powerful representations of pre-trained Vi

Revisiting the Volume Hypothesis

arXiv:2606.31282v1 Announce Type: new Abstract: Modern deep neural networks often contain far more parameters than needed to fit their training data, yet they achieve impressive generalization. A comm

safetyarxiv-cs-lg

Revocable Learned State via Process Sidecars

arXiv:2606.30788v1 Announce Type: cross Abstract: Language models are often adapted in stages: a public skill phase, a private memory phase, and a later safety phase that learns to refuse outputs tied

safetyarxiv-cs-cl

Reward Redistribution for CVaR MDPs using a Bellman Operator on L-infinity

arXiv:2602.03778v2 Announce Type: replace-cross Abstract: Tail-end risk measures such as static conditional value-at-risk (CVaR) are used in safety-critical applications to prevent rare, yet catastrop

RGBT-GroundBench: Visual Grounding Beyond RGB in Complex Real-World Scenarios

arXiv:2512.24561v2 Announce Type: replace Abstract: Visual grounding (VG) localizes target objects in an image from natural-language expressions. In real-world perception, RGB cues often degrade under

Rhythm-Structured Predictive Learning for Remote Photoplethysmography

arXiv:2606.31736v1 Announce Type: new Abstract: Remote photoplethysmography (rPPG) estimates physiological signals from facial videos by analyzing subtle pulse induced skin color variations. Despite r

safetyarxiv-cs-cv

RigorBench: Benchmarking Engineering Process Discipline in Autonomous AI Coding Agents

model-releasesarxiv-cs-ai

arXiv:2606.22678v2 Announce Type: replace-cross Abstract: Agentic coding harnesses - such as Agent-Skills, Superpowers, and Agent-Rigor - are increasingly deployed to augment underlying LLMs for real-