research

Statistical Inference and Quality Measures of KV Cache Quantisations Inspired by TurboQuant

arXiv:2605.08114v1 Announce Type: new Abstract: We analyse three KV cache quantization schemes under a fair bit budget: extbf{KV} (scalar MSE baseline), extbf{KQV} (WHT + MSE on K; WHT + MSE + QJL on

Research

Stealthy Patch-Wise Backdoor Attack in 3D Point Cloud via Curvature Awareness

DGX agent

arXiv:2503.09336v4 Announce Type: replace Abstract: Backdoor attacks pose a severe threat to deep neural networks (DNNs) by implanting hidden backdoors that can be activated with predefined triggers t

researcharxiv-cs-cv

12 May 2026

Stellar Age Compression Reshapes Interpretations of the Milky Way Thick-Disk Formation History

arXiv:2605.10220v1 Announce Type: cross Abstract: The formation timescale of the Milky Way thick disk is one of the central debates in Galactic archaeology. The age-metallicity relation (AMR), formati

Step 3.5 Flash from @StepFun_ai is now free again in Nous Portal for the next 15 days!

Nous Research announced that Step 3.5 Flash, an AI model from StepFun, is temporarily available for free on the Nous Portal for a 15-day period. This offer provides users access to the model without c

researchnous-research--x

Streaming Sliced Optimal Transport

arXiv:2505.06835v4 Announce Type: replace Abstract: Sliced optimal transport (SOT), or sliced Wasserstein (SW) distance, is widely recognized for its statistical and computational scalability. In this

Structure-Centric Graph Foundation Model via Geometric Bases

arXiv:2605.08689v1 Announce Type: cross Abstract: Graph foundation models (GFMs) seek transferable representations across graph domains but are limited by structural heterogeneity and incompatible nod

Structured Recurrent Mixers for Massively Parallelized Sequence Generation

arXiv:2605.08696v1 Announce Type: new Abstract: Over the last two decades, language modeling has experienced a shift from predominantly recurrent architectures that process tokens sequentially during

Sufficient conditions for a Heuristic Rating Estimation Method application

arXiv:2605.08991v1 Announce Type: new Abstract: A series of papers has introduced the Heuristic Rating Estimation method, which evaluates a set of alternatives based on pairwise comparisons and the we

Supersampling Stable Diffusion and More: An Approach for Interpolating Neural Networks Using Common Interpolation Methods

arXiv:2605.08698v1 Announce Type: new Abstract: Stable Diffusion (SD) has evolved DDPM (Denoising Diffusion Probabilistic Model) based image generation significantly by denoising in latent space inste

Supervised Dimensionality Reduction Revisited: Why LDA on Frozen CNN Features Deserves a Second Look

arXiv:2604.03928v2 Announce Type: replace-cross Abstract: Frozen pretrained image representations are widely used for transfer learning: a backbone is kept fixed, feature vectors are extracted, and a

Supervised Guidance Training for Infinite-Dimensional Diffusion Models

arXiv:2601.20756v2 Announce Type: replace Abstract: Score-based diffusion models have recently been extended to infinite-dimensional function spaces, with uses such as inverse problems arising from pa

Survey on Disaster Management Datasets for Remote Sensing Based Emergency Applications

arXiv:2605.08196v1 Announce Type: new Abstract: Recent natural disasters have highlighted the urgent need for efficient data-driven approaches to disaster management. Machine learning (ML) and deep le

Symbolic learning is not a replacement for coding agents, it's a replacement for gradient descent & NNs: a low-level, completely general, ex…

researchfrancois-chollet--x

Francois Chollet argues that symbolic learning represents a fundamental alternative to gradient descent and neural networks rather than a replacement for coding agents, offering a low-level, general-p

SynerDiff: Synergetic Continuous Batching for Fast and Parallel Diffusion Model Inference

arXiv:2605.08835v1 Announce Type: new Abstract: The expansion of Artificial Intelligence-generated content service requires diffusion model serving to simultaneously achieve high throughput and low ta

TAD: Temporal-Aware Trajectory Self-Distillation for Fast and Accurate Diffusion LLM

arXiv:2605.09536v1 Announce Type: cross Abstract: Diffusion large language models (dLLMs) offer a promising paradigm for parallel text generation, but in practice they face an accuracy-parallelism tra

TAH-QUANT: Effective Activation Quantization in Pipeline Parallelism over Slow Network

arXiv:2506.01352v2 Announce Type: replace Abstract: Decentralized training of large language models offers the opportunity to pool computational resources across geographically distributed participant

TARO: Temporal Adversarial Rectification Optimization Using Diffusion Models as Purifiers

arXiv:2605.08440v1 Announce Type: cross Abstract: Adversarial purification with diffusion models seeks to project adversarial examples back toward the data manifold, but balancing semantic preservatio

Task-Agnostic Noisy Label Detection via Standardized Loss Aggregation

arXiv:2605.10165v1 Announce Type: cross Abstract: Noisy labels are common in large-scale medical imaging datasets due to inter-observer variability and ambiguous cases. We propose a statistically grou

Task-Aware Calibration: Provably Optimal Decoding in LLMs

arXiv:2605.10202v1 Announce Type: cross Abstract: LLM decoding often relies on the model's predictive distribution to generate an output. Consequently, misalignment with respect to the true generating

Task complexity shapes internal representations and robustness in neural networks

arXiv:2508.05463v2 Announce Type: replace-cross Abstract: Neural networks excel across a wide range of tasks, yet remain black boxes. In particular, how their internal representations are shaped by th

TELL-TALE: Task Efficient LLMs with Task Aware Layer Elimination

arXiv:2510.22767v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) typically come with a fixed architecture, despite growing evidence that not all layers contribute equally to ever

Temporal-Decay Shapley: A Time-Aware Data Valuation Framework for Time-Series Data

arXiv:2605.08153v1 Announce Type: new Abstract: With the rapid development of machine learning applications on time-series data, accurately assessing the value of training samples has become essential

Tensor Product Representation Probes Reveal Shared Structure Across Linear Directions

arXiv:2605.09967v1 Announce Type: new Abstract: While researchers are finding concepts represented as linear directions in language models, a bag of linear directions fails to capture relational struc

Test-Time Training for Visual Foresight Vision-Language-Action Models

arXiv:2605.08215v1 Announce Type: new Abstract: Visual Foresight VLA (VF-VLA) has become a prominent architectural choice in the recent VLA due to its impressive performance. Nevertheless, the inheren

The Association of Transformer-based Sentiment Analysis with Symptom Distress and Deterioration in Routine Psychotherapy Care

arXiv:2605.09838v1 Announce Type: new Abstract: Sentiment analysis has been of long-standing interest in psychotherapy research. Recently, the Transformer deep learning architecture has produced text-

The Astonishing Ability of Large Language Models to Parse Jabberwockified Language

arXiv:2602.23928v2 Announce Type: replace Abstract: We show that large language models (LLMs) have an astonishing ability to recover meaning from severely degraded English texts. Texts in which conten

The Benefits of Temporal Correlations: SGD Learns k-Juntas from Random Walks Efficiently

arXiv:2605.10237v1 Announce Type: new Abstract: We study how temporal correlations in the data can make certain sparse learning problems efficiently learnable by gradient-based methods. Our focus is o

The Cancellation Hypothesis in Critic-Free RL: From Outcome Rewards to Token Credits

arXiv:2605.08666v1 Announce Type: new Abstract: A commonly accepted explanation of critic-free RL for LLMs, based on sequence-level rewards, is that it reinforces successful rollouts with a positive a

The Cartesian Shortcut: Re-evaluate Vision Reasoning in Polar Coordinate Space

arXiv:2605.09883v1 Announce Type: cross Abstract: As current Multimodal Large Language Models rapidly saturate canonical visual reasoning benchmarks, a key question emerges: do these strong scores gen

The Direct Integration Theorem: A Rigorous Framework for Consistent Discrete Solutions of the Inverse Radon Problem

arXiv:2605.09020v1 Announce Type: new Abstract: This paper presents a novel Direct Integration Theorem (DIT), derived as a non-trivial corollary of the classical Central Slice Theorem (CST). The DIT p

The Download: a Nobel winner on AI, and the case for fixing everything

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. Three things in AI to watch, according to a Nobel-winning econ

researchmit-tech-review

The DSA's Blind Spot: Algorithmic Audit of Advertising and Minor Profiling on TikTok

arXiv:2603.05653v2 Announce Type: replace-cross Abstract: Adolescents spend an increasing amount of their time in digital environments where their still-developing cognitive capacities leave them unab

The Ensemble Schr{odinger Bridge filter for Nonlinear Data Assimilation

arXiv:2512.18928v3 Announce Type: replace Abstract: This work introduces a novel nonlinear optimal filtering method, termed the Ensemble Schr{odinger Bridge nonlinear filter. The proposed filter combi

The Generalized Turing Test: A Foundation for Comparing Intelligence

arXiv:2605.10851v1 Announce Type: new Abstract: We introduce the Generalized Turing Test (GTT), a formal framework for comparing the capabilities of arbitrary agents via indistinguishability. For agen

The Geometric Reasoner: Manifold-Informed Latent Foresight Search for Long-Context Reasoning

arXiv:2601.18832v3 Announce Type: replace-cross Abstract: Scaling test-time compute enhances long chain-of-thought (CoT) reasoning, yet existing approaches face a fundamental trade-off between computa

The Impact of Editorial Intervention on Detecting Native Language Traces

arXiv:2605.10216v1 Announce Type: new Abstract: Native Language Identification (NLI) is the task of determining an author's native language (L1) from their non-native writings. With the advent of huma

The Invisible Handshake: Persistent Overpricing by Adaptive Market Agents

arXiv:2510.15995v3 Announce Type: replace-cross Abstract: We study overpricing in a repeated game between two representative agents: a market maker, who controls market liquidity, and a market taker,

The Mixing method: low-rank coordinate descent for semidefinite programming with diagonal constraints

arXiv:1706.00476v4 Announce Type: replace-cross Abstract: In this paper, we propose a low-rank coordinate descent approach to structured semidefinite programming with diagonal constraints. The approac

The Observable Wasserstein Distance

arXiv:2605.09916v1 Announce Type: cross Abstract: We introduce the observable Wasserstein distance, a framework for deriving lower bounds on the Wasserstein distance between probability measures on Po

The Open-Box Fallacy: Why AI Deployment Needs a Calibrated Verification Regime

arXiv:2605.10601v1 Announce Type: new Abstract: AI deployment in sensitive domains such as health care, credit, employment, and criminal justice is often treated as unsafe to authorize until model int

The Polynomial Counting Capabilities of Message Passing Neural Networks

arXiv:2605.10393v1 Announce Type: new Abstract: The counting power of Message Passing Neural Networks (MPNN) has been the subject of many recent papers, showing that they can express logic that involv

The Power of Second Order Methods for Sequence Preconditioning

arXiv:2605.08390v1 Announce Type: new Abstract: Sequence prediction methods for dynamical systems with long memory, i.e. marginally stable systems, typically achieve regret that grows polynomially wit

The Propagation Field: A Geometric Substrate Theory of Deep Learning

arXiv:2605.08529v1 Announce Type: new Abstract: Modern deep learning treats neural networks primarily as endpoint functions from inputs to outputs. Inspired by the shift from force to geometry in phys

The Sample Complexity of Uniform Approximation for Multi-Dimensional CDFs and Fixed-Price Mechanisms

arXiv:2602.10868v2 Announce Type: replace Abstract: We study the sample complexity of learning a uniform approximation of an n-dimensional cumulative distribution function (CDF) within an error epsilo

Thinking with Novel Views: A Systematic Analysis of Generative-Augmented Spatial Intelligence

arXiv:2605.10588v1 Announce Type: new Abstract: Current Large Multimodal Models (LMMs) struggle with spatial reasoning tasks requiring viewpoint-dependent understanding, largely because they are confi

Threat Modelling using Domain-Adapted Language Models: Empirical Evaluation and Insights

arXiv:2605.10808v1 Announce Type: cross Abstract: Large Language Models(LLMs) are increasingly explored for cybersecurity applications such as vulnerability detection. In the domain of threat modellin

Tighter Information-Theoretic Generalization Bounds via a Novel Class of Change of Measure Inequalities

arXiv:2602.07999v3 Announce Type: replace-cross Abstract: Change of measure inequalities translate divergences between probability measures into explicit bounds on event probabilities, and play an imp

TileQ: Efficient Low-Rank Quantization of Mixture-of-Experts with 2D Tiling

arXiv:2605.09281v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models achieve remarkable performance by sparsely activating specialized experts, yet their massive parameters in experts pose