model releases

Quasi-Linear ICA for Motor Unit Decomposition during Dynamic Contractions

arXiv:2406.19581v2 Announce Type: replace-cross Abstract: Decomposing surface electromyography (EMG) into the spike trains of individual motor neurons is a long-standing inverse problem and a key step

Model Releases

Queryable LoRA: Instruction-Regularized Routing Over Shared Low-Rank Update Atoms

DGX agent

arXiv:2605.08423v1 Announce Type: cross Abstract: We present a data-adaptive method for parameter-efficient fine-tuning of large neural networks. Standard low-rank adaptation methods improve efficienc

model-releasesarxiv-cs-cl

12 May 2026

Qwen Goes Brrr: Off-the-Shelf RAG for Ukrainian Multi-Domain Document Understanding

arXiv:2605.10296v1 Announce Type: cross Abstract: We participated in the Fifth UNLP shared task on multi-domain document understanding, where systems must answer Ukrainian multiple-choice questions fr

Qwen-Image-2.0 Technical Report

arXiv:2605.10730v1 Announce Type: new Abstract: We present Qwen-Image-2.0, an omni-capable image generation foundation model that unifies high-fidelity generation and precise image editing within a si

R4Det: 4D Radar-Camera Fusion for High-Performance 3D Object Detection

arXiv:2603.11566v2 Announce Type: replace Abstract: 4D radar-camera sensing configuration has gained increasing importance in autonomous driving. However, existing 3D object detection methods that fus

RadThinking: A Dataset for Longitudinal Clinical Reasoning in Radiology

arXiv:2605.10761v1 Announce Type: new Abstract: Cancer screening is a reasoning task. A radiologist observes findings, compares them to prior scans, integrates clinical context, and reaches a diagnost

RareCP: Regime-Aware Retrieval for Efficient Conformal Prediction

arXiv:2605.08857v1 Announce Type: new Abstract: Recent advances in uncertainty quantification for time series forecasting show that conformal prediction can provide reliable prediction intervals, yet

RDEx-CASK: Cauchy Mutation, Archive, and Stagnation Kick for RDEx-CSOP

arXiv:2605.09652v1 Announce Type: cross Abstract: We extend RDEx-CSOP with 3 changes that target stagnation & late-stage variance, plus minor parameter tuning. The second scale factor in the standard

Re^2Math: Benchmarking Theorem Retrieval in Research-Level Mathematics

arXiv:2605.09012v1 Announce Type: new Abstract: Large language models are increasingly capable at closed-world mathematical reasoning, but research assistance also requires source-grounded use of the

Real vs. Semi-Simulated: Rethinking Evaluation for Treatment Effect Estimation

arXiv:2605.10430v1 Announce Type: cross Abstract: Estimating heterogeneous treatment effects with machine learning has attracted substantial attention in both academic research and industrial practice

Really amazing dissection. LLMs hitting rarely. Tools list is amazing.

model-releasesgary-marcus--x

Really amazing dissection. LLMs hitting rarely. Tools list is amazing. 🤩🤯🤩 Claude Code (still not AGI but biggest advance since GPT-4) is the most neurosymbolic thing I have ever seen in my life. 53 s

ReaMOT: A Benchmark and Framework for Reasoning-based Multi-Object Tracking

arXiv:2505.20381v4 Announce Type: replace Abstract: Referring Multi-Object Tracking (RMOT) aims to track targets specified by language instructions. However, existing RMOT paradigms heavily rely on ex

REAP: Automatic Curation of Coding Agent Benchmarks from Interactive Production Usage

arXiv:2604.01527v3 Announce Type: replace-cross Abstract: Production deployment of AI coding agents requires fast, reproducible evaluation signals. Existing industrial practices trade off speed and fi

Reasoning emerges from constrained inference manifolds in large language models

arXiv:2605.08142v1 Announce Type: cross Abstract: Reasoning in large language models is predominantly evaluated through labeled benchmarks, conflating task performance with the quality of internal inf

Recovering Physical Dynamics from Discrete Observations via Intrinsic Differential Consistency

arXiv:2605.08454v1 Announce Type: cross Abstract: Recovering continuous-time dynamics from discrete observations is difficult because local supervision (e.g., pointwise regression targets, derivative

Recursive Language Models

arXiv:2512.24601v3 Announce Type: replace Abstract: We study allowing large language models (LLMs) to process arbitrarily long prompts through the lens of inference-time scaling. We propose Recursive

REI-Bench: Can Embodied Agents Understand Vague Human Instructions in Task Planning?

arXiv:2505.10872v4 Announce Type: replace-cross Abstract: Robot task planning decomposes human instructions into executable action sequences that enable robots to complete a series of complex tasks. A

Reinforcement Learning Measurement Model

arXiv:2605.09305v1 Announce Type: cross Abstract: Interactive assessments generate sequential process data that are not well handled by conventional item response models. Existing MDP-based measuremen

Relative Kinetic Utility for Reasoning-Aware Structural Pruning in Large Language Models

arXiv:2605.09008v1 Announce Type: cross Abstract: Chain-of-Thought (CoT) prompting symbolized a huge improvement of reasoning capabilities of Large Language Models (LLMs). However, scaling up test-tim

RelBench v2: A Large-Scale Benchmark and Repository for Relational Data

arXiv:2602.12606v2 Announce Type: replace Abstract: Relational deep learning (RDL) has emerged as a powerful paradigm for learning directly on relational databases by modeling entities and their relat

Reliable LLM-Based Edge-Cloud-Expert Cascades for Telecom Knowledge Systems

arXiv:2512.20012v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are emerging as key enablers of automation in domains such as telecommunications, assisting with tasks including

Rennala MVR: Improved Time Complexity for Parallel Stochastic Optimization via Momentum-Based Variance Reduction

arXiv:2605.08871v1 Announce Type: cross Abstract: Large-scale machine learning models are trained on clusters of machines that exhibit heterogeneous performance due to hardware variability, network de

ReorgGS: Equivalent Distribution Reorganization for 3D Gaussian Splatting

arXiv:2605.08739v1 Announce Type: new Abstract: A converged 3D Gaussian Splatting (3DGS) model may approximate the target scene while remaining poorly parameterized for further optimization. We identi

Repeated-Token Counting Reveals a Dissociation Between Representations and Outputs

arXiv:2605.09239v1 Announce Type: new Abstract: Large language models fail at counting repeated tokens despite strong performance on broader reasoning benchmarks. These failures are commonly attribute

ReplaySCM: A Benchmark for Executable Causal Mechanism Induction from Interventions

arXiv:2605.08197v1 Announce Type: cross Abstract: Most causal benchmarks for language models score local answers or graph structure. We introduce ReplaySCM, a 1,300 item benchmark for executable causa

Rethinking Agentic Search with Pi-Serini: Is Lexical Retrieval Sufficient?

arXiv:2605.10848v1 Announce Type: cross Abstract: Does a lexical retriever suffice as large language models (LLMs) become more capable in an agentic loop? This question naturally arises when building

Rethinking Random Transformers as Adaptive Sequence Smoothers for Sleep Staging

arXiv:2605.09905v1 Announce Type: cross Abstract: Automatic sleep staging commonly adopts Transformers under the assumption that they learn complex long-range dependencies. We challenge this view by r

Retrieval Mechanisms Surpass Long-Context Scaling in Time Series Forecasting

arXiv:2605.08217v1 Announce Type: new Abstract: Time Series Foundation Models (TSFMs) have borrowed the long context paradigm from natural language processing under the premise that feeding more histo

Retrieve-then-Steer: Online Success Memory for Test-Time Adaptation of Generative VLAs

arXiv:2605.10094v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models show strong potential for general-purpose robotic manipulation, yet their closed-loop reliability often degrades u

RewardHarness: Self-Evolving Agentic Post-Training

arXiv:2605.08703v1 Announce Type: new Abstract: Evaluating instruction-guided image edits requires rewards that reflect subtle human preferences, yet current reward models typically depend on large-sc

RoboMemArena: A Comprehensive and Challenging Robotic Memory Benchmark

model-releasesarxiv-cs-ro

arXiv:2605.10921v1 Announce Type: new Abstract: Memory is a critical component of robotic intelligence, as robots must rely on past observations and actions to accomplish long-horizon tasks in partial

Robust Server Defense Against Unreliable Clients in One-Shot Fair Collaborative Machine Learning

arXiv:2605.08616v1 Announce Type: new Abstract: Collaborative machine learning (CML) enables multiple clients to train a global model jointly in a data-distributed setting. To address data privacy and

Robust Spectral Watermark for Synthetic Tabular Data

arXiv:2511.21600v2 Announce Type: replace-cross Abstract: The rise of generative AI has enabled the production of high-fidelity synthetic tabular data across fields such as healthcare, finance, and pu

ROM: Real-time Overthinking Mitigation via Streaming Detection and Intervention

arXiv:2603.22016v2 Announce Type: replace-cross Abstract: Large Reasoning Models (LRMs) often reach a correct solution before their long Chain-of-Thought trace ends, yet continue with redundant verifi

Route Before Retrieve: Activating Latent Routing Abilities of LLMs for RAG vs. Long-Context Selection

arXiv:2605.10235v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) have expanded the context window to beyond 128K tokens, enabling long-document understanding and multi-s

RubricRefine: Improving Tool-Use Agent Reliability with Training-Free Pre-Execution Refinement

arXiv:2605.09730v1 Announce Type: new Abstract: Iterative self-refinement is a popular inference-time reliability technique, but its effectiveness in code-mode tool use depends heavily on the structur

RW-Post: Auditable Evidence-Grounded Multimodal Fact-Checking in the Wild

arXiv:2605.10357v1 Announce Type: cross Abstract: Multimodal misinformation increasingly leverages visual persuasion, where repurposed or manipulated images strengthen misleading text. We introduce ex

S2FT: Parameter-Efficient Fine-Tuning in Sparse Spectrum Domain

arXiv:2605.08589v1 Announce Type: new Abstract: Parameter Efficient Fine-Tuning (PEFT) is a key technique for adapting a large pretrained model to downstream tasks by fine-tuning only a small number o

SACHI: Structured Agent Coordination via Holistic Information Integration in Multi-Agent Reinforcement Learning

arXiv:2605.08391v1 Announce Type: new Abstract: Cooperative multi-agent reinforcement learning agents that act on partial local observations face a fundamental information bottleneck: the knowledge ne

SAFA-SNN: Sparsity-Aware On-Device Few-Shot Class-Incremental Learning with Fast-Adaptive Structure of Spiking Neural Network

arXiv:2510.03648v2 Announce Type: replace Abstract: Continuous learning of novel classes is crucial for edge devices to preserve data privacy and maintain reliable performance in dynamic environments.

SAP SAPPHIRE 2026: Google Cloud unveils unified agentic vision and massive compute scaling

model-releasesgoogle-cloud-ai

In today's hyper-connected market, an enterprise's most valuable asset — mission-critical data — often remains trapped in legacy silos. For years, leadership teams have navigated a data pipeline dilem

SayNext-Bench: Why Do LLMs Struggle with Next-Utterance Anticipation?

arXiv:2602.00327v2 Announce Type: replace Abstract: We explore the use of large language models (LLMs) for next-utterance anticipation in human dialogue. Despite recent advances in LLMs demonstrating

Scalable Gaussian process inference via neural feature maps

arXiv:2605.10285v1 Announce Type: cross Abstract: We present a theoretically grounded Gaussian process framework that leverages neural feature maps to construct expressive kernels. We show that the le

SCALAR: A Neurosymbolic Framework for Automated Conjecture and Reasoning in Quantum Circuit Analysis

arXiv:2605.10327v1 Announce Type: cross Abstract: In this paper, we present SCALAR (Symbolic Conjecture and LLM-Assisted Reasoning), a neurosymbolic framework for automated conjecture generation in qu

Scaling Limits of Long-Context Transformers

arXiv:2605.08505v1 Announce Type: cross Abstract: We study the long-context limit of softmax self-attention with a fixed query and a random context of n i.i.d. keys on the sphere, viewing the inverse

Scaling the Memory of Balanced Adam

arXiv:2605.10119v1 Announce Type: new Abstract: Recent evidence suggests that Adam performs robustly when its momentum parameters are tied, eta_1=eta_2, reducing the optimizer to a single remaining pa

Scaling Vision Models Does Not Consistently Improve Localisation-Based Explanation Quality

arXiv:2605.10142v1 Announce Type: cross Abstract: Artificial intelligence models are increasingly scaled to improve predictive accuracy, yet it remains unclear whether scale improves the quality of po

Scam2Prompt: A Scalable Framework for Auditing Malicious Scam Endpoints in Production LLMs

arXiv:2509.02372v3 Announce Type: replace-cross Abstract: Large Language Models have become critical to modern software development, but their reliance on uncurated web-scale datasets for training int