research

Revisiting Positive Samples in Graph Contrastive Learning: From the Perspective of Message Passing

arXiv:2606.10284v1 Announce Type: new Abstract: Graph Contrastive Learning (GCL), which trains graph encoders by maximizing similarity between positive samples and minimizing it between negative ones,

Research

Risk Comparisons in Linear Regression: Implicit Regularization Dominates Explicit Regularization

DGX agent

arXiv:2509.17251v2 Announce Type: replace-cross Abstract: Existing theory suggests that for linear regression problems categorized by capacity and source conditions, gradient descent (GD) is always mi

researcharxiv-cs-lg

10 Jun 2026

RKSC: Reasoning-Aware KV Cache Sharing and Confident Early Exit for Multi-Step LLM Inference

arXiv:2606.09937v1 Announce Type: cross Abstract: We introduce RKSC (Reasoning-Aware KV Cache Sharing), a training-free inference framework that eliminates two structural redundancies in multi-branch

Robotic Nonprehensile Object Transportation with a Hanging Tray

arXiv:2606.10039v1 Announce Type: new Abstract: We consider the nonprehensile object transportation task known as the waiter's problem, in which a robot must move an object balanced on a tray from one

researcharxiv-cs-ro

Robust Active Learning for Few-Shot Example Selection in Text-to-SQL

arXiv:2606.10125v1 Announce Type: cross Abstract: Few-shot example retrieval is the dominant paradigm for grounding large language models (LLMs) in domain-specific text-to-SQL systems. However, the qu

ros2probe: Non-intrusive, Kernel-selective Observability for Robot Operating System 2 Middleware

arXiv:2606.10746v1 Announce Type: new Abstract: Robot Operating System 2 (ROS 2), the de facto standard middleware framework for robots, runs each robot as a graph of nodes communicating over the Data

researcharxiv-cs-ro

Routing-Aware Expert Calibration for Machine Unlearning in Mixture-of-Experts Language Models

arXiv:2606.10338v1 Announce Type: cross Abstract: Machine unlearning is increasingly important for large language models, yet unlearning in Mixture-of-Experts (MoE) architectures remains underexplored

Scaling Self-Supervised Speech Models Uncovers Deep Linguistic Relationships: Evidence from the Pacific Cluster

arXiv:2603.07238v2 Announce Type: replace Abstract: Similarities between language representations derived from Self-Supervised Speech Models (S3Ms) have been observed to primarily reflect geographic p

Schmidt Decomposition-Based Methods for Efficient Quantum Image Encoding

arXiv:2606.10874v1 Announce Type: new Abstract: In quantum image processing, a fundamental step is encoding classical image data into quantum states. This can be achieved using methods such as Flexibl

Seal-Robust KCR: A Robust Kuzushiji Character Recognition Framework under Seal Interference

arXiv:2602.19086v2 Announce Type: replace Abstract: Kuzushiji was one of the most widely used cursive writing systems in pre-modern Japan. Due to its highly cursive forms and extensive glyph variation

Secure Aggregation with Top-K Sparsification in Decentralized Federated Learning

arXiv:2606.10780v1 Announce Type: cross Abstract: Secure aggregation is a vital component for mitigating gradient leakage in federated learning, but its communication cost conventionally scales with t

Segment and Select: Vision-Language Segmentation in 3D Scenarios

arXiv:2606.10594v1 Announce Type: new Abstract: 3D vision-language segmentation aims to segment target objects in 3D scenarios according to the linguistic instructions and visual observations. Prior a

Sleep EEG Signal Criticality as a Non-Invasive Predictor of Cognitive Decline in Dementia

arXiv:2606.10889v1 Announce Type: cross Abstract: Early detection of neurodegeneration remains a critical clinical challenge. This study investigates whether sleep EEG signal criticality, quantified v

Some considerations that many folks seem not to get: 1. It can be a bubble even if the tech works. (For instance, if the tech doesn't have a…

researchfrancois-chollet--x

Some considerations that many folks seem not to get: 1. It can be a bubble even if the tech works. (For instance, if the tech doesn't have a high-demand use case.) 2. It can be a bubble even if the te

Soul Computing: A Theoretical Framework and Technical Architecture for Intelligent Agents with Independent Consciousness

arXiv:2606.10413v1 Announce Type: new Abstract: Breakthroughs in large language models and multimodal generation technologies have propelled the digital reconstruction of human mental traits, emotiona

SPACR: Single-Pass Adaptive Training of Uncertainty-Aware Conformal Regressors

arXiv:2606.10734v1 Announce Type: new Abstract: Conformal Prediction (CP) provides robust uncertainty guarantees for predictive models, but is typically applied post hoc, which misaligns model trainin

Spatio-Temporal Attention Graph Neural Network: Explaining Causalities With Attention

arXiv:2603.10676v2 Announce Type: replace Abstract: Industrial Control Systems (ICS) underpin critical infrastructure and face growing cyber-physical threats due to the convergence of operational tech

Speech Meets ELF: Audio Conditional Continuous-Target Diffusion for Speech Recognition and Translation

arXiv:2606.10368v1 Announce Type: cross Abstract: Speech-to-text (S2T) systems for recognition (ASR) and translation (S2TT) typically generate discrete text tokens. In contrast, continuous-target lang

Spiking Neural Network inference on FPGAs with hls4ml

arXiv:2606.10008v1 Announce Type: cross Abstract: Spiking Neural Networks (SNNs) provide a naturally temporal machine-learning framework. Their neurons maintain an internal state and propagate informa

Stochastic weather generators for high-frequency wind vector time series

arXiv:2606.09941v1 Announce Type: cross Abstract: Surface winds can vary substantially from one minute to the next, so there is scope for studying its variation on this fine time scale. Restricting to

STORM: Stepwise Token Optimization with Reward-Guided Beam Search

arXiv:2606.10621v1 Announce Type: cross Abstract: Modern retrieval increasingly relies on dense and learned-sparse neural models that are effective but require encoding the entire corpus into a specia

Structured Adaptive Tensor Prediction for Streaming Data

arXiv:2606.10085v1 Announce Type: new Abstract: Matrix-valued time series arise in a wide range of applications, such as spatio-temporal data from medical imaging and geophysics. Existing methods are

Superficial Beliefs in LLM Decision-Making

arXiv:2606.11016v1 Announce Type: new Abstract: We ask whether large language models (LLMs) merely imitate rationales when choosing between two options, or whether their choices reflect a systematic u

The Bioelectrical Information Theory: Investigating the theoretical compression limit of bioelectrical signals under artificial intelligence

arXiv:2606.09922v1 Announce Type: cross Abstract: Bioelectrical signals are increasingly acquired at scales that challenge the bandwidth of brain-computer interfaces. However, their compression is sti

The Download: the “steroid olympics” and a safer Mythos

This is today’s edition of The Download, our weekday newsletter that provides a daily dose of what’s going on in the world of technology. The “steroid olympics” were a circus—and a window into our cul

researchmit-tech-review

The Emergence of Reproducibility and Generalizability in Diffusion Models

arXiv:2310.05264v5 Announce Type: replace-cross Abstract: In this work, we investigate an intriguing and prevalent phenomenon of diffusion models which we term as 'consistent model reproducibility': g

The “steroid olympics” were a circus—and a window into our culture

Testosterone. Methenolone. Nandrolone. Human growth hormone and EPO. Meldonium, modafinil, and mixed amphetamine salts. Clomiphene, anastrozole, levothyroxine, and liothyronine. Patches and capsules,

researchmit-tech-review

The videos from the “Frontiers of Embodied AI” meetup at ETHZ from a few weeks back are now available. Speakers: Jitendra Malik, Vladlen Kol…

The videos from the “Frontiers of Embodied AI” meetup at ETHZ from a few weeks back are now available. Speakers: Jitendra Malik, Vladlen Koltun, Yann LeCun, and Shuran Song Hosted by Marc Pollefeys Yo

researchyann-lecun--x

This is awesome! I am spending a lot of time on diffusion LLMs these days, so this is perfect timing. I feel like there are so many underexp…

This is awesome! I am spending a lot of time on diffusion LLMs these days, so this is perfect timing. I feel like there are so many underexplored research questions around text diffusion. Weight avail

researchdair-ai--x

This is why frontier open models are crucial. This is extremely sad for the research community.

This is why frontier open models are crucial. This is extremely sad for the research community. mythos will be bad ON PURPOSE on ai 'frontier llm research' tasks, this is very very sad for the researc

researchdair-ai--x

Time Series as Language: A Universal Tokenizer for General-Purpose Time Series Foundation Models

arXiv:2606.09861v1 Announce Type: cross Abstract: While Next-Token Prediction (NTP) has unified LLM pretraining, its adaptation to unbounded, continuous time series (TS) remains open. To bridge the ga

Time series forecasting from partial observations via Non-negative Matrix Factorization

arXiv:2102.05314v2 Announce Type: replace Abstract: In modern time series problems, one aims at forecasting multiple time series with possible missing and noisy values. In this paper, we introduce the

Towards Critical Branching Mechanism in Recurrent Neural Networks

arXiv:2606.10384v1 Announce Type: cross Abstract: Criticality has been proposed as a key organizing principle in biological neural systems, yet its origin and relevance in artificial neural networks r

Towards Diverse Scientific Hypothesis Search with Large Language Models

arXiv:2606.10587v1 Announce Type: cross Abstract: Large language models (LLMs) are on the rise for accelerating scientific discovery, most recently in advanced tasks such as generating valid scientifi

Towards Robust Arabic Speech Emotion Recognition with Deep Learning

arXiv:2606.10278v1 Announce Type: cross Abstract: Speech Emotion Recognition (SER) aims to identify a speaker's emotional state from audio signals. While recent advances in deep learning have signific

Trainability of IQP Quantum Circuit Born Machines Under Gaussian Initialization

arXiv:2606.10179v1 Announce Type: cross Abstract: Quantum Circuit Born Machines (QCBMs) offer a natural approach to generative machine learning by leveraging the Born rule. Recent work has provided a

Training Set Augmentation and Biology-Aware Harmonization Improve Radiomic Models for Lung Cancer Prediction in Indeterminate Nodules

arXiv:2412.16758v3 Announce Type: replace-cross Abstract: CT radiomics-based machine learning has potential to predict lung cancer in pulmonary nodules (PNs) earlier than standard-of-care methods. Low

TruthRL: Incentivizing Truthful LLMs via Reinforcement Learning

arXiv:2509.25760v2 Announce Type: replace-cross Abstract: While large language models (LLMs) have demonstrated strong performance on factoid question answering, they are still prone to hallucination a

Uncertainty-Aware Deep Learning for Wildfire Danger Forecasting

arXiv:2509.25017v2 Announce Type: replace-cross Abstract: Wildfires are among the most severe natural hazards, posing a significant threat to both humans and natural ecosystems. The growing risk of wi

Uncertainty-aware Multi-fidelity Closure via Conditional Normalizing Flows

arXiv:2606.09857v1 Announce Type: new Abstract: Reduced-order models (ROMs) provide an efficient surrogate for complex multiscale systems, but their predictive accuracy is often compromised by truncat

UniDexTok: A Unified Dexterous Hand Tokenizer from Real Data

arXiv:2606.10683v1 Announce Type: cross Abstract: Dexterous hands are essential for fine-grained manipulation, but their hardware designs vary substantially across embodiments. Differences in kinemati

UniSVQ: 2-bit Unified Scalar-Vector Quantization

arXiv:2606.10520v1 Announce Type: new Abstract: Post-training quantization at the 2-bit level enables low-cost deployment and inference acceleration for large language models (LLMs). Scalar quantizati

Unsupervised Deep Learning for Limited-Angle STEM-EDX Tomography -- Application to 3D Chemical Analysis of Phase-Change Memory Devices

arXiv:2606.10547v1 Announce Type: cross Abstract: Energy Dispersive X-ray (EDX) tomography in Scanning Transmission Electron Microscopy (STEM) enables 3D compositional and elemental mapping at the nan

Upper Bounds for Local Learning Coefficients of Three-Layer Neural Networks

arXiv:2603.12785v2 Announce Type: replace Abstract: Three-layer neural networks are known to form singular learning models, and their Bayesian asymptotic behavior is governed by the learning coefficie

VFUSE: Virulent Feature Understanding with Sparse autoEncoders

arXiv:2606.10080v1 Announce Type: cross Abstract: Generative models have shown remarkable progress in a variety of domains such as protein design, but such power enables the opaque generation of hazar

What Do Deepfake Speech Detectors Actually Hear?

arXiv:2606.10912v1 Announce Type: cross Abstract: Deepfake speech detectors often output a single score without explaining why an audio sample is flagged, where in the signal the evidence lies, or wha

What Really Matters for Table LLMs? A Meta-Evaluation of Model and Data Effects

arXiv:2501.14717v2 Announce Type: replace Abstract: Table modeling has progressed for decades. In this work, we revisit this trajectory and highlight emerging challenges in the LLM era, particularly t

When Metrics Disagree: A Meta-Analysis of Knowledge-Graph-Completion Model Benchmarking

arXiv:2606.10287v1 Announce Type: cross Abstract: Evaluating Knowledge Graph Completion (KGC) models remains challenging because standard assessment relies on isolated rank-based metrics such as MRR,