research

Geometry-Aware Sampling-Based Motion Planning on Riemannian Manifolds

arXiv:2602.00992v2 Announce Type: replace Abstract: In many robot motion planning problems, task objectives and physical constraints induce non-Euclidean geometry on the configuration space, yet many

researcharxiv-cs-ro

Graphs of Research: Citation Evolution Graphs as Supervision for Research Idea Generation

DGX agent

arXiv:2605.14790v1 Announce Type: cross Abstract: Research idea generation is the innovation-driving step of automated scientific research. Recently, large language models (LLMs) have shown potential

researcharxiv-cs-ai

15 May 2026

Guided Diffusion Sampling for Precipitation Forecast Interventions

arXiv:2605.14317v1 Announce Type: new Abstract: Extreme precipitation causes severe societal and economic damage, and weather control has long been discussed as a potential mitigation strategy. Howeve

HASTE: Training-Free Video Diffusion Acceleration via Head-Wise Adaptive Sparse Attention

arXiv:2605.14513v1 Announce Type: cross Abstract: Diffusion-based video generation has advanced substantially in visual fidelity and temporal coherence, but practical deployment remains limited by the

Head Forcing: Long Autoregressive Video Generation via Head Heterogeneity

arXiv:2605.14487v1 Announce Type: cross Abstract: Autoregressive video diffusion models support real-time synthesis but suffer from error accumulation and context loss over long horizons. We discover

HERO: Hierarchical Extrapolation and Refresh for Efficient World Models

arXiv:2508.17588v2 Announce Type: replace Abstract: Generation-driven world models create immersive virtual environments but suffer slow inference due to the iterative nature of diffusion models. Whil

HodgeCover: Higher-Order Topological Coverage Drives Compression of Sparse Mixture-of-Experts

arXiv:2605.13997v1 Announce Type: cross Abstract: Sparse Mixture-of-Experts (MoE) layers route tokens through a handful of experts, and learning-free compression of these layers reduces inference cost

How Chinese short dramas became AI content machines

In a dimly lit bedroom, a frightened young woman is thrown onto a bed by a tall, muscular man. He grabs her hand, and flame-like vines crawl across her body, fusing with her flesh. She levitates, then

researchmit-tech-review

How well behaved is finite dimensional Diffusion Maps?

arXiv:2412.03992v3 Announce Type: replace-cross Abstract: Under a set of assumptions on a family of submanifolds subset {mathbb R}^D, we derive a series of geometric properties that remain valid after

If you have this weird gut feeling that the rich pay little tax in the US, your gut is spot on... Source: https://www.nytimes.com/interactiv…

If you have this weird gut feeling that the rich pay little tax in the US, your gut is spot on... Source: https://www.nytimes.com/interactive/2019/10/06/opinion/income-tax-rate-wealthy.html?action=cli

researchyann-lecun--x

Image Restoration via Diffusion Models with Dynamic Resolution

arXiv:2605.14267v1 Announce Type: cross Abstract: Diffusion models (DMs) have exhibited remarkable efficacy in various image restoration tasks. However, existing approaches typically operate within th

Implicit spatial-frequency fusion of hyperspectral and lidar data via kolmogorov-arnold networks

arXiv:2605.14239v1 Announce Type: new Abstract: Hyperspectral image (HSI) classification is challenging in complex scenes due to spectral ambiguity, spatial heterogeneity, and the strong coupling betw

Improving Multi-turn Dialogue Consistency with Self-Recall Thinking

arXiv:2605.15102v1 Announce Type: cross Abstract: Large language model (LLM) based multi-turn dialogue systems often struggle to track dependencies across non-adjacent turns, undermining both consiste

InsightTok: Improving Text and Face Fidelity in Discrete Tokenization for Autoregressive Image Generation

arXiv:2605.14333v1 Announce Type: new Abstract: Text and faces are among the most perceptually salient and practically important patterns in visual generation, yet they remain challenging for autoregr

Interestingness as an Inductive Heuristic for Future Compression Progress

arXiv:2605.14831v1 Announce Type: new Abstract: One of the bottlenecks on the way towards recursively self-improving systems is the challenge of interestingness: the ability to prospectively identify

Iskra: A System for Inverse Geometry Processing

arXiv:2602.12105v2 Announce Type: replace-cross Abstract: We propose a system for differentiating through solutions to geometry processing problems. Our system differentiates a broad class of geometri

IsoNet: Spatially-aware audio-visual target speech extraction in complex acoustic environments

arXiv:2605.14736v1 Announce Type: cross Abstract: Target speech extraction remains difficult for compact devices because monaural neural models lack spatial evidence and classical beamformers lose res

It Takes Two: Your GRPO Is Secretly DPO

arXiv:2510.00977v3 Announce Type: replace-cross Abstract: GRPO has emerged as a prominent reinforcement learning algorithm for post-training LLMs. Unlike critic-based methods, GRPO computes advantages

Keyed Nonlinear Transform: Lightweight Privacy-Enhancing Feature Sharing for Medical Image Analysis

arXiv:2605.14123v1 Announce Type: cross Abstract: Feature sharing via split inference offers a lightweight alternative to federated learning for resource-constrained hospitals, but transmitted feature

Knowledge Beyond Language: Bridging the Gap in Multilingual Machine Unlearning Evaluation

arXiv:2605.14404v1 Announce Type: new Abstract: While LLMs are increasingly used in commercial services, they pose privacy risks such as leakage of sensitive personally identifiable information (PII).

Large Dimensional Kernel Ridge Regression: Extending to Product Kernels

arXiv:2605.14524v1 Announce Type: cross Abstract: Recent studies have reported extit{saturation effects} and extit{multiple descent behavior} in large dimensional kernel ridge regression (KRR). Howeve

Learning Dynamic Rope Manipulation Using Task-Level Iterative Learning Control

arXiv:2602.21302v2 Announce Type: replace Abstract: We introduce a Task-Level Iterative Learning Control method for dynamic manipulation of ropes. We demonstrate this method on a non-planar rope manip

researcharxiv-cs-ro

Learning Multimodal Embeddings for Traffic Accident Prediction and Causal Estimation

arXiv:2512.02920v3 Announce Type: replace-cross Abstract: We consider analyzing traffic accident patterns using both road network data and satellite images aligned to road graph nodes. Previous work f

Learning Scenario Reduction for Two-Stage Robust Optimization with Discrete Uncertainty

arXiv:2605.14494v1 Announce Type: new Abstract: Two-Stage Robust Optimization (2RO) with discrete uncertainty is challenging, often rendering exact solutions prohibitive. Scenario reduction alleviates

Leveraging Speech to Identify Signatures of Insight and Transfer in Problem Solving

arXiv:2605.12970v2 Announce Type: replace Abstract: Many problems seem to require a flash of insight to solve. What form do these sudden insights take, and what impact do they have on how people appro

LLM-based Detection of Manipulative Political Narratives

arXiv:2605.14354v1 Announce Type: new Abstract: We present a new computational framework for detecting and structuring manipulative political narratives. A task that became more important due to the s

LLM-Based Robustness Testing of Microservice Applications: An Empirical Study

arXiv:2605.14202v1 Announce Type: cross Abstract: Malformed, missing, or boundary-value inputs in microservice APIs can cascade across dependent services, threatening reliability. Robustness testing s

LoRIF: Low-Rank Influence Functions for Scalable Training Data Attribution

arXiv:2601.21929v2 Announce Type: replace Abstract: Training data attribution (TDA) identifies which training examples most influenced a model's prediction. Influence function methods are a theoretica

LoVeC: Reinforcement Learning for Better Verbalized Confidence in Long-Form Generations

arXiv:2505.23912v2 Announce Type: replace-cross Abstract: Hallucination remains a major challenge for the safe and trustworthy deployment of large language models (LLMs) in factual content generation.

M^2RNN: Non-Linear RNNs with Matrix-Valued States for Scalable Language Modeling

arXiv:2603.14360v2 Announce Type: replace-cross Abstract: Transformers are highly parallel but are limited to computations in the TC^0 complexity class, excluding tasks such as entity tracking and cod

MambaRain: Multi-Scale Mamba-Attention Framework for 0-3 Hour Precipitation Nowcasting

arXiv:2605.14606v1 Announce Type: new Abstract: Accurate precipitation nowcasting over extended horizons (0-3 hours) is essential for disaster mitigation and operational decision-making, yet remains a

MAPLE: Self-Supervised Learning-Enhanced Nonlinear Dimensionality Reduction for Visual Analysis

arXiv:2601.20173v2 Announce Type: replace Abstract: We present a new nonlinear dimensionality reduction method, MAPLE, that enhances UMAP by improving manifold modeling. MAPLE employs a self-supervise

Measuring Google AI Overviews: Activation, Source Quality, Claim Fidelity, and Publisher Impact

arXiv:2605.14021v1 Announce Type: cross Abstract: Google AI Overviews (AIOs) are arguably the most widely encountered deployment of generative AI, reaching over 2 billion users who may not realize the

Med-DisSeg: Dispersion-Driven Representation Learning for Fine-Grained Medical Image Segmentation

arXiv:2605.14579v1 Announce Type: new Abstract: Accurate medical image segmentation is fundamental to precision medicine, yet robust delineation remains challenging under heterogeneous appearances, am

Meschers: Geometry Processing of Impossible Objects

arXiv:2605.14960v1 Announce Type: cross Abstract: Impossible objects, geometric constructions that humans can perceive but that cannot exist in real life, have been a topic of intrigue in visual arts,

MetaMoE: Diversity-Aware Proxy Selection for Privacy-Preserving Mixture-of-Experts Unification

arXiv:2605.14289v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) models scale capacity by combining specialized experts, but most existing approaches assume centralized access to training da

Metis AI: The Overlooked Middle Zone Between AI-Native and World-Movers

arXiv:2605.14407v1 Announce Type: new Abstract: The dominant discourse on AI limitations frames the boundary of AI capability as a divide between digital tasks (where AI excels) and physical tasks (wh

MHSA: A Lightweight Framework for Mitigating Hallucinations via Steered Attention in LVLMs

arXiv:2605.14966v1 Announce Type: cross Abstract: Large vision-language models (LVLMs) have achieved remarkable performance across diverse multimodal tasks, yet they continue to suffer from hallucinat

MicroscopyMatching: Towards a Ready-to-use Framework for Microscopy Image Analysis in Diverse Conditions

arXiv:2605.14980v1 Announce Type: cross Abstract: Analyzing microscopy images to extract biological object properties (e.g., their morphological organization, temporal dynamics, and population density

Mitigating Data Scarcity in Psychological Defense Classification with Context-Aware Synthetic Augmentation

arXiv:2605.14380v1 Announce Type: new Abstract: Psychological defense mechanisms (PDMs) are unconscious cognitive processes that modulate how individuals perceive and respond to emotional distress. Au

MiVE: Multiscale Vision-language features for reference-guided video Editing

arXiv:2605.14664v1 Announce Type: new Abstract: Reference-guided video editing takes a source video, a text instruction, and a reference image as inputs, requiring the model to faithfully apply the in

Monitoring Data-aware Temporal Properties (Extended Version)

arXiv:2605.14666v1 Announce Type: new Abstract: Dynamic systems in AI are often complex and heterogeneous, so that an internal specification is not accessible and verification techniques such as model

MonoPRIO: Adaptive Prior Conditioning for Unified Monocular 3D Object Detection

arXiv:2605.14781v1 Announce Type: new Abstract: Monocular 3D object detection remains challenging because metric size and depth are underdetermined by single-view evidence, particularly under occlusio

Most documented psychological biases are not irrational, they are highly optimized, energy-efficient shortcuts meant for a biological substr…

researchfrancois-chollet--x

Most documented psychological biases are not irrational, they are highly optimized, energy-efficient shortcuts meant for a biological substrate operating under strict real-time physical constraints an

MPU: Towards Secure and Privacy-Preserving Knowledge Unlearning for Large Language Models

arXiv:2602.23798v2 Announce Type: replace-cross Abstract: Machine unlearning for large language models often faces a privacy dilemma in which strict constraints prohibit sharing either the server's pa

Multi-Block Attention for Efficient Channel Estimation in IRS-Assisted mmWave MIMO

arXiv:2605.15032v1 Announce Type: cross Abstract: Intelligent Reflecting Surfaces (IRSs) are a promising technology for enhancing the spectral and energy efficiency of millimeter-wave (mmWave) multipl

Multi-proposal Collaboration and Multi-task Training for Weakly-supervised Video Moment Retrieval

arXiv:2605.14838v1 Announce Type: new Abstract: This study focuses on weakly-supervised Video Moment Retrieval (VMR), aiming to identify a moment semantically similar to the given query within an untr

Multi-Scale Dequant: Eliminating Dequantization Bottleneck via Activation Decomposition for Efficient LLM Inference

arXiv:2605.13915v1 Announce Type: cross Abstract: Quantization is essential for efficient large language model (LLM) inference, yet the dequantization step-converting low-bit weights back to high-prec