Search: “research”

Getting to the Point: Pointing Improves LVLMs at Counting

arXiv:2603.21746v2 Announce Type: replace Abstract: Pointing-based methods decompose complex tasks as sequential grounding and reasoning steps. Given a query, the model first grounds the relevant obje

GiPL: Generative augmented iterative Pseudo-Labeling for Cross-Domain Few-Shot Object Detection

DGX agent

arXiv:2605.29539v1 Announce Type: cross Abstract: Vision-language foundation models have shown promising zero-shot generalization for Cross-Domain Few-Shot Object Detection (CD-FSOD). However, they fa

researcharxiv-cs-ai

29 May 2026

GPS-Enhanced Tourist Mobility Modeling with Seasonal Spatial Priors and LLM-Based Activity Chain Generation

arXiv:2605.29578v1 Announce Type: new Abstract: Tourist mobility poses a distinct challenge for urban transportation planning. Unlike resident commuting, tourist travel is largely non-routine, attract

Gradient Preconditioning for Efficient and Reliable Reward-Guided Generation

arXiv:2602.08646v2 Announce Type: replace Abstract: We propose a gradient preconditioning method that makes reward-guided generation with one-step generative models both efficient and reliable. Test-t

GRASP: Plan-Guided Graph Retrieval with Adaptive Fusion and Reranking on Semi-Structured Knowledge Bases

arXiv:2605.30237v1 Announce Type: cross Abstract: Semi-structured knowledge bases (SKBs) embed textual documents in a typed graph of entities and relations, and underpin applications such as product s

HaluNet: Learning Hallucination Risk from Internal Signals in LLM Question Answering

arXiv:2512.24562v2 Announce Type: replace Abstract: Large language models (LLMs) achieve strong question answering (QA) performance but can produce fluent answers unsupported by available evidence. Ex

HARP: Hadamard-Preconditioned Adaptive Rotation Processor for Extreme LLM Quantization

arXiv:2605.29843v1 Announce Type: cross Abstract: Post-training quantization (PTQ) is essential for deploying LLMs under memory and bandwidth constraints. However, extreme low-bit quantization remains

HiKEY: Hierarchical Multimodal Retrieval for Open-Domain Document Question Answering

arXiv:2605.29606v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) for document-based Open-domain Question Answering (ODQA) on large-scale industrial corpora faces two critical bottl

HM-Talker: Hybrid Motion Modeling for High-Fidelity Talking Head Synthesis

arXiv:2508.10566v3 Announce Type: replace Abstract: Audio-driven talking head generation faces a fundamental trade-off between personalization and generalization, limiting its practical application. I

HoliTok:A Coutinuous Holistic Tokenization with Robust Dual Capabilities of Speech Generation and Understanding

arXiv:2605.29948v1 Announce Type: cross Abstract: Unified speech foundation models require a holistic tokenization space that is both learnable by language models and decodable into high-quality wavef

Honest Lying: Understanding Memory Confabulation in Reflexive Agents

arXiv:2605.29463v1 Announce Type: cross Abstract: Reflexion-style agents rely on self-generated reflections as memory, implicitly assuming that agents can accurately diagnose their own failures.We sho

Horizon Activation Mapping for Neural Networks in Time Series Forecasting

arXiv:2601.02094v4 Announce Type: replace Abstract: Neural networks for time series forecasting have relied on error metrics and architecture-specific interpretability approaches for model selection t

How Much Is a Dataset Worth? Scaling Laws, the Vendi Score, and Matrix Spectral Functions

arXiv:2605.29448v1 Announce Type: cross Abstract: Neural scaling laws appraise data through dataset size, while the Vendi Score uses quantum entropy to measure dataset value. We show both that common

How the Pope’s Magnifica Humanitas offers a template for individuals to meet the AI moment

Pope Leo XIV’s new encyclical on artificial intelligence includes a statement that warrants serious attention from technologists and policymakers: “Technology is never neutral.” Magnifica Humanitas (“

researchmit-tech-review

Implicit Identity Technologies for LLMs: Fingerprinting and Watermarking across Datasets, Models, and Generated Content

arXiv:2605.29245v1 Announce Type: cross Abstract: This paper presents a survey and taxonomy of LLM fingerprinting and watermarking for identity, ownership verification, provenance, and generated-conte

Improved Guarantees for Heterogeneous Treatment-Effect Estimation via Matrix Completion

arXiv:2605.30319v1 Announce Type: cross Abstract: A central goal of modern causal inference is estimating heterogeneous treatment effects to answer questions like 'how does an intervention affect each

In-Place Feedback: Reliable Refinement for Multi-Turn Expert-LLM Collaboration

arXiv:2510.00777v2 Announce Type: replace Abstract: LLM-generated drafts often contain subtle factual or logical errors, yet prior work shows that models struggle to reliably integrate multi-turn feed

Inspectorch: Efficient rare event exploration in solar observations

arXiv:2602.20316v2 Announce Type: replace-cross Abstract: The Sun is observed in unprecedented detail, enabling studies of its activity on very small spatiotemporal scales. However, the large volume o

Instance-dependent Stochastic Lipschitz bandit

arXiv:2605.29748v1 Announce Type: cross Abstract: We study the Lipschitz bandit problem, where a learner sequentially maximizes an unknown Lipschitz function f over a domain X subset [0,1]^d using noi

Interactive In-Meeting Speaker Correction with Human Feedback

arXiv:2509.18377v2 Announce Type: replace Abstract: Most automatic speech processing systems operate in ``open loop'' mode without user feedback about who said what, yet human-in-the-loop workflows ca

Is Your Diffusion Sampler Actually Correct? A Sampler-Centric Evaluation of Discrete Diffusion Language Models

arXiv:2602.19619v2 Announce Type: replace Abstract: Discrete diffusion language models (dLLMs) provide a fast and flexible alternative to autoregressive models (ARMs) via iterative denoising with para

Joint Model and Data Sparsification via the Marginal Likelihood

arXiv:2605.29908v1 Announce Type: cross Abstract: Sparse recovery in linear systems underpins applications from signal processing to high-dimensional regression. Sparse Bayesian Learning, grounded in

KLAS: Using Similarity to Stitch Neural Networks for Improved Accuracy-Efficiency Tradeoffs

arXiv:2605.29259v1 Announce Type: cross Abstract: Given the wide range of deployment targets, flexible model selection is essential for optimizing performance within a given compute budget. Recent wor

LaRA: Layer-wise Representation Analysis for Detecting Data Contamination in RL Post-Training

arXiv:2605.29888v1 Announce Type: cross Abstract: Reinforcement learning (RL) post-training has shown to improve reasoning in large language models (LLMs). However, there has been little exploration o

Learning Context-Conditioned Predicate Semantics via Prototype Feedback

arXiv:2605.29610v1 Announce Type: cross Abstract: In scene graph generation, a central challenge is modeling polysemous predicates whose meanings shift across contexts. Prior approaches address this i

Learning to Perturb Hidden Representations for Generalizable Deep Learning

arXiv:2605.29525v1 Announce Type: new Abstract: Deep neural networks process data through a cascade of representations: input features, hidden activations, logits, and loss. While perturbations at the

Leave a Window Out: Modifying the Jackknife for Predictive Inference in Time Series

arXiv:2605.30292v1 Announce Type: cross Abstract: Conformal prediction methods enjoy strong theoretical and empirical predictive inference performance, provided the data is exchangeable, and predictor

Lexical categories of stem-forming roots in Mapudungun verb forms

arXiv:2502.07623v4 Announce Type: replace Abstract: After developing a computational system for morphological analysis of the Mapuche language, and evaluating it with texts from various authors and st

LFQ: Logit-aware Final-block Quantization for Boosting the Generation Quality of Low-Bit Quantized LLMs

arXiv:2605.29756v1 Announce Type: new Abstract: As large language models continue to scale, low-bit weight-only post-training quantization (PTQ) offers a practical solution to their memory-efficient d

Lightweight Complementary-Cue Fusion for Robust Video Face Forgery Detection

arXiv:2605.29092v1 Announce Type: new Abstract: Current face video forgery detectors use wide or dual-stream backbones. We show that a single, lightweight fusion of two handcrafted cues can achieve hi

Lightweight Multimodal LLM-Enabled Cost-Effective Defect Grading of Power Transmission Equipment

arXiv:2605.28822v1 Announce Type: new Abstract: Defect grading of power transmission equipment (DGPTE) is crucial to the stability of electric energy transmission. Although existing machine learning m

LLMBridge: An LLM Pipeline for End-to-end Referential Bridging Resolution in English

arXiv:2605.29048v1 Announce Type: new Abstract: In this paper, we introduce LLMBridge, a new LLM based system for the task of end-to-end referential bridging resolution in English. Our bridging resolu

LLMSurgeon: Diagnosing Data Mixture of Large Language Models

arXiv:2605.30348v1 Announce Type: cross Abstract: The pretraining data mixture of Large Language Models (LLMs) constitutes their 'digital DNA', shaping model behaviors, capabilities, and failure modes

LoRe: Adaptive Interaction-Evaluation Routing with Per-Step Interaction Budgets for Iterative Graph Solvers

arXiv:2605.29005v1 Announce Type: cross Abstract: Diffusion-based neural solvers for combinatorial optimization repeatedly re-evaluate dense edge/factor interactions, making inference expensive in wal

Manifold-based Algorithms for the Hadamard Decomposition

arXiv:2605.28980v1 Announce Type: cross Abstract: Given a matrix X, and two ranks r_1 and r_2, the Hadamard decomposition (HD) looks for two low-rank matrices, X_1 of rank r_1 and X_2 of rank r_2, bot

MARTIAN: A Rendering Framework for Aerial Mars Imagery from HiRISE Orbital Data

arXiv:2605.29647v1 Announce Type: new Abstract: Aerial navigation on Mars requires vision-based pipelines that are robust to the diverse illumination conditions and terrain morphology of the Martian s

Masked Diffusion Vision-Language Models for Temporal Action Localization

arXiv:2605.29858v1 Announce Type: new Abstract: Temporal action localization (TAL) requires recognizing the target event and localizing its start and end times precisely in untrimmed videos. Recent vi

Matching Rates and Optimal Allocation for Federated Probe-Logit Distillation under Heterogeneous Bandwidth Budgets

arXiv:2605.29642v1 Announce Type: cross Abstract: In federated language modeling, K nodes each hold n samples but cannot pool data or exchange full-precision gradients or weights. We study the minimax

Matrix Completion with Hypergraphs:Sharp Thresholds and Efficient Algorithms

arXiv:2401.08197v3 Announce Type: replace Abstract: This paper considers the problem of completing a rating matrix based on sub-sampled matrix entries as well as observed social graphs and hypergraphs

Measure flow path recovery in Bayes Hilbert spaces

arXiv:2603.20329v2 Announce Type: replace-cross Abstract: We study the ill-posed problem of recovering a probability measure flow from finitely many moving localized sensors using a Bayes Hilbert fram

MEC: Machine-Learning-Assisted Generalized Entropy Calibration for Semi-Supervised Mean Estimation

arXiv:2604.05446v2 Announce Type: replace-cross Abstract: Obtaining high-quality labels is costly, whereas unlabeled covariates are often abundant, motivating semi-supervised inference methods with re

Mechanism Shift During Post-training from Autoregressive to Masked Diffusion Language Models

arXiv:2601.14758v4 Announce Type: replace-cross Abstract: Post-training pretrained autoregressive models (ARMs) into masked diffusion models (MDMs) has emerged as a cost-effective way to overcome the

MedCase-Structured: A Text-to-FHIR Dataset for Benchmarking Diagnostic Reasoning in Clinically Realistic EHR Settings

arXiv:2605.30295v1 Announce Type: cross Abstract: Large language models (LLMs) show promise for clinical reasoning and decision support, but evaluation in realistic, electronic health record-congruent

MELD: Mel-Spectrogram-Based Speech Language Modeling with Discrete Latent Variables

arXiv:2605.29859v1 Announce Type: cross Abstract: Recent speech language models rely on encoders that are optimized separately from autoregressive models. Since these encoders are unaware of the downs

MemoSight: Unifying Context Compression and Multi Token Prediction for Reasoning Acceleration

arXiv:2604.14889v2 Announce Type: replace Abstract: While chain-of-thought (CoT) reasoning enables LLMs to solve challenging reasoning tasks, the linear growth of the KV cache leads to substantial mem

Mesh-Aware Epipolar Matching for Multi-View Multi-Person 3D Pose Estimation in Basketball

arXiv:2605.29953v1 Announce Type: new Abstract: Multi-view multi-person 3D pose estimation in team sports scenarios remains challenging due to player occlusions, appearance similarity caused by team u

Meta-Programming for Linear-time Temporal Answer Set Programming

arXiv:2605.29965v1 Announce Type: new Abstract: The development of temporal extensions of Answer Set Programming (ASP) has led to the emergence of non-monotonic linear-time (TEL), dynamic (DEL), and m

MiAD: Mirage Atom Diffusion for De Novo Crystal Generation

arXiv:2511.14426v2 Announce Type: replace-cross Abstract: In recent years, diffusion-based models have demonstrated exceptional performance in searching for simultaneously stable, unique, and novel (S