research

TANDEM: Bi-Level Data Mixture Optimization with Twin Networks

arXiv:2606.04401v1 Announce Type: new Abstract: The capabilities of large language models (LLMs) significantly depend on training data drawn from various domains. Optimizing domain-specific mixture ra

Teaching Robots to Say 'I Don't Know' : SENTINEL for Uncertainty-Aware SLAM

DGX agent

arXiv:2606.04853v1 Announce Type: new Abstract: Low-cost 2D LiDARs lack the intensity channel that higher-end sensors use to diagnose measurement failures, yet they are widely used on educational and

researcharxiv-cs-ro

4 Jun 2026

The Download: AI-generated lawsuits and virtual power plants for data centers

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. How courts are coping with a flood of AI-generated lawsuits Mo

researchmit-tech-review

The future of quantum takes center stage at NY Tech Week

IBM Research highlighted quantum computing developments and applications at NY Tech Week, showcasing the technology's potential impact on industry and research. The event featured discussions on quant

researchibm-research

The price of multi-group transductive learning

arXiv:2606.04423v1 Announce Type: new Abstract: We show every multi-group learner in the transductive setting may incur a multiplicative penalty in its error rate on some group relative to the error r

This is too good to keep to myself. I will be sharing more on how I am using dynamic workflows and how and why I built my own version of it:…

The post announces that the author will share insights about their use of dynamic workflows and explain their reasoning behind building a custom implementation. This likely covers practical applicatio

researchdair-ai--x

Tight Long-Term Tail Decay of (Clipped) SGD in Non-Convex Optimization

arXiv:2602.05657v2 Announce Type: replace Abstract: The study of tail behaviour of SGD-induced processes has been attracting a lot of interest, due to offering strong guarantees with respect to indivi

Token Rankings are Unforgeable Language Model Signatures

arXiv:2606.04459v1 Announce Type: cross Abstract: Language model parameters are known to impose unique (to each model) geometric constraints on their logit outputs, which serves as a signature that id

Tomography by Design: An Algebraic Approach to Low-Rank Quantum States

arXiv:2602.15202v2 Announce Type: replace-cross Abstract: We present an algebraic algorithm for quantum state tomography that leverages measurements of certain observables to estimate structured entri

Towards Accurate Model Selection in Deep Unsupervised Domain Adaptation

arXiv:2606.04665v1 Announce Type: new Abstract: Deep unsupervised domain adaptation (Deep UDA) methods successfully leverage rich labeled data in a source domain to boost the performance on related bu

Towards passive heart health monitoring via smartphone camera

Google Research developed PHRM, a deep-learning system that uses facial video-based photoplethysmography to passively measure heart rate and resting heart rate during everyday smartphone use . The sys

researchgoogle-research

TPA-AD: A Two-Stage Pseudo Anomaly-Guided Method for Bearing Time-Series Anomaly Detection

arXiv:2606.04073v1 Announce Type: cross Abstract: This paper proposes a two-stage pseudo anomaly-guided anomaly detection method (extbf{T}wo-stage extbf{P}seudo extbf{A}nomaly-guided extbf{A}nomaly ex

Training-Free Lexical-Dense Fusion for Conversational-Memory Retrieval

arXiv:2606.04194v1 Announce Type: cross Abstract: Retrieving the few past turns that answer a new query across long multi-session histories is the retrieval bottleneck behind long-term conversational

Translation Heads: Disentangling meaning from language in LLM-based machine translation

arXiv:2602.04613v2 Announce Type: replace Abstract: Mechanistic Interpretability (MI) seeks to explain how neural networks implement their capabilities, but the scale of Large Language Models (LLMs) h

Transmuting prompts into weights

arXiv:2510.08734v3 Announce Type: replace Abstract: A growing body of research has demonstrated that the behavior of large language models can be effectively controlled at inference time by directly m

T^star: Progressive Block Scaling for Masked Diffusion Language Models Through Trajectory Aware Reinforcement Learning

arXiv:2601.11214v5 Announce Type: replace Abstract: We present T^star, a simple TraceRL-based training curriculum for progressive block-size scaling in masked diffusion language models (MDMs). Startin

Uncertainty Estimation using Variance-Gated Distributions

arXiv:2509.08846v2 Announce Type: replace-cross Abstract: Evaluation of per-sample uncertainty quantification from neural networks is essential for decision-making involving high-risk applications. A

Uncovering Insights of Compound Flooding with Data-Driven AI

arXiv:2506.04281v2 Announce Type: replace Abstract: Compound flooding, driven by nonlinear interactions between multiple hydrometeorological factors, poses a significant challenge to hazard prevention

UniCanvas: A Diffusion-base Unified Model for Text-in-Image Joint Generation

arXiv:2606.04264v1 Announce Type: new Abstract: Recent years have seen remarkable progress in unified vision-language models handling both multimodal understanding and generation within a single archi

UniFine: A Unified and Fine-grained Approach for Zero-shot Vision-Language Understanding

arXiv:2307.00862v3 Announce Type: replace-cross Abstract: Vision-language tasks, such as VQA, SNLI-VE, and VCR are challenging because they require the model's reasoning ability to understand the sema

Unifying Information-Theoretic and Pair-Counting Clustering Similarity

arXiv:2511.03000v2 Announce Type: replace-cross Abstract: Comparing clusterings is central to evaluating unsupervised models, yet the many existing similarity measures can produce widely divergent, so

Unlocking Feature Learning in Gated Delta Networks at Scale

arXiv:2606.04048v1 Announce Type: cross Abstract: Training and scaling Large Language Models demand enormous computational resources, motivating both efficient sub-quadratic architectures and principl

Validity Threats for Foundation Model Research

arXiv:2606.05029v1 Announce Type: cross Abstract: Controlled experiments are the backbone of machine learning research, but at the scale of modern foundation models, they have become prohibitively exp

Variance-Gated Ensembles: An Epistemic-Aware Framework for Uncertainty Estimation

arXiv:2602.08142v2 Announce Type: replace Abstract: Machine learning applications require fast and reliable per-sample uncertainty estimation. A common approach is to use predictive distributions from

ViewMask-1-to-3: Multi-View Consistent Image Generation via Multimodal Discrete Diffusion Models

arXiv:2512.14099v3 Announce Type: replace Abstract: Motivated by discrete diffusion's success in language-vision modeling, we explore its potential for multi-view generation, a task dominated by conti

Vision Transformer Finetuning Benefits from Non-Smooth Components

arXiv:2602.06883v3 Announce Type: replace-cross Abstract: The smoothness of the transformer architecture has been extensively studied in the context of generalization, training stability, and adversar

Weakly Supervised Incremental Segmentation via Semantic Anchors and Spatial Arbitration

arXiv:2606.04060v1 Announce Type: new Abstract: Weakly Incremental Learning for Semantic Segmentation (WILSS) suffers from the continuous introduction of noisy supervision, which progressively corrupt

When and why randomised exploration works (in linear bandits)

arXiv:2502.08870v2 Announce Type: replace Abstract: We provide an approach for the analysis of randomised exploration algorithms like Thompson sampling that does not rely on forced optimism or posteri

When Clients Stop Following: A Cognitive Conceptualization Diagram-driven Framework for Strategic Counseling

arXiv:2606.04389v1 Announce Type: new Abstract: Large Language Models (LLMs) show promise in psychological counseling, yet existing benchmarks rely heavily on highly cooperative simulated clients. We

When Detectors Forget Forensics: Blocking Semantic Shortcuts for Generalizable AI-Generated Image Detection

arXiv:2603.09242v2 Announce Type: replace Abstract: The growing realism of generative models has blurred the boundary between real and synthetic content, posing significant challenges to reliable AI-g

When Freshness Is Not Enough: Distribution-Aware Age of Information for Networked LQR Control

arXiv:2606.04361v1 Announce Type: cross Abstract: Age of Information (AoI) has become a central metric for the design of wireless update systems, especially in applications where fresh measurements su

researcharxiv-cs-ro

When Offline Selectors Cannot Beat the Best Single Model: A Diagnostic Study on edX Dropout Prediction

arXiv:2606.04161v1 Announce Type: new Abstract: Different predictors often excel on different inputs, so picking the best one per instance promises higher accuracy than committing to a single model. I

When Retrieval Doesn't Help: A Large-Scale Study of Biomedical RAG

arXiv:2606.04127v1 Announce Type: new Abstract: Medical question answering is a high-stakes setting where factual errors can have serious consequences. Retrieval-augmented generation (RAG) is widely v

Who Needs Labels? Adapting Vision Foundation Models With the Metadata You Already Have

arXiv:2606.05107v1 Announce Type: cross Abstract: We propose a label-free approach to adapt powerful but generic vision foundation models to specialized scientific domains. Standard supervised fine-tu

Why Japanese companies do so many different things: The internal logic of the world’s strangest corporations https://davidoks.blog/p/why-jap…

Why Japanese companies do so many different things: The internal logic of the world’s strangest corporations https://davidoks.blog/p/why-japanese-companies-do-so-many TL;DR > you have a firm that has

researchdavid-ha--x

Worker Utility as Hysteresis: A Preisach Model of Transaction Acceptance in Gig Labour Markets

arXiv:2606.04916v1 Announce Type: new Abstract: Worker utility is not observed -- only its consequence is. Each gig transaction produces a single bit: accepted or rejected. We argue this structure poi

You Only Train Once: Differentiable Subset Selection for Omics Data

arXiv:2512.17678v2 Announce Type: replace-cross Abstract: Selecting compact and informative gene subsets from single-cell transcriptomic data is essential for biomarker discovery, improving interpreta

ZipSplat: Fewer Gaussians, Better Splats

arXiv:2606.05102v1 Announce Type: new Abstract: Feed-forward 3D Gaussian Splatting methods reconstruct a scene from posed or pose-free images in a single forward pass, yet current approaches predict o

A cross-domain tropical species dataset with Chinese vernacular names and CITES source links

arXiv:2606.03156v1 Announce Type: new Abstract: We describe a versioned cross-domain dataset of 410,499 active tropical species (working snapshot 2026-04-20) spanning three applied subdomains -- tropi

A Factorized Low-Rank RNN Framework for Uncovering Independent Neural Latent Dynamics and Connectivity

arXiv:2511.13899v2 Announce Type: replace-cross Abstract: Low-rank recurrent neural networks (lrRNNs) are a class of models that uncover low-dimensional latent dynamics underlying neural population ac

A Fast Screening Approach for High-dimensional Outcomes and High-dimensional Predictors

arXiv:2606.03018v1 Announce Type: cross Abstract: Modeling interactions among multimodal, high-dimensional data is intrinsically challenging due to ultra-high dimensionality and complex dependence str

A formal definition and meta-model for a machine theory of mind

arXiv:2606.03471v1 Announce Type: new Abstract: This paper proposes, for the first time, a rigorous formal definition of the concept of Machine Theory of Mind, based on principles supported by evidenc

A Hybrid Approach For Malware Classification Using Secondary Features Fusion

arXiv:2606.03432v1 Announce Type: cross Abstract: The number of malware (either variant or novel) is rapidly increasing, making malware detection and mitigation a complex problem. One approach to impr

A Measurement-Driven Digital Twin Architecture for Plant-Level Biomass Estimation and Growth Forecasting in Hydroponic Systems

arXiv:2606.02796v1 Announce Type: new Abstract: Alternatives to soil-based horticulture, such as hydroponics, have been developed to respond to food distribution concerns for dense urban centers. A ne

researcharxiv-cs-ro

A Quantitative Approximation Framework for Flow Distillation in Diffusion Models

arXiv:2606.03820v1 Announce Type: cross Abstract: We develop a quantitative approximation framework for diffusion distillation, viewing few-step sampling as error propagation under compositions of lea

A Scoping Review of the Ethical Perspectives on Anthropomorphising Large Language Model-Based Conversational Agents

arXiv:2601.09869v2 Announce Type: replace Abstract: Anthropomorphisation -- the phenomenon whereby non-human entities are ascribed human-like qualities -- has become increasingly salient with the rise

A Sparse Bayesian Learning Algorithm for Estimation of Interaction Kernels in Motsch-Tadmor Model

arXiv:2505.07068v2 Announce Type: replace-cross Abstract: In this paper, we investigate the data-driven identification of asymmetric interaction kernels in the Motsch-Tadmor model based on observed tr

AAD-1: Asymmetric Adversarial Distillation for One-Step Autoregressive Video Generation

arXiv:2606.03972v1 Announce Type: new Abstract: We present AAD-1, an Asymmetric Adversarial Distillation framework for One-step autoregressive image-to-video generation. State-of-the-art methods adopt