Search: “research”

Fast Unlearning at Scale via Margin Self-Correction

arXiv:2606.02920v1 Announce Type: new Abstract: Language-model unlearning updates a trained model to behave as if it had not seen selected training examples, while preserving utility and avoiding cost

Finding Needles in the Haystack: Transductive Active Labeling in Ecology

DGX agent

arXiv:2606.03821v1 Announce Type: new Abstract: Active learning is now standard practice in labeling ecological data, enabling ecologists to quickly process large volumes of field data to understand a

researcharxiv-cs-lg

3 Jun 2026

Fixed-Time Dynamic Landing of Quadrotors using Adaptive Unscented Kalman Filtering and Nonlinear Model Predictive Control

arXiv:2606.02658v1 Announce Type: new Abstract: This paper introduces an estimation and control framework for dynamic landing of multi-rotor uncrewed aerial vehicles on moving platforms. The proposed

FlashbackCL: Mitigating Temporal Forgetting in Federated Learning

arXiv:2606.03939v1 Announce Type: cross Abstract: Federated Learning (FL) of foundation and edge models increasingly targets deployments where client data distributions drift over time, yet existing f

Flicker-DDPM: Accelerating Denoising Diffusion via 1/f Colored Noise Injection

arXiv:2606.03393v1 Announce Type: new Abstract: We propose a novel diffusion model, Flicker-DDPM, which incorporates flicker (1/f) noise inspired by self-organized criticality (SOC), a widely observed

FLIPS: Instance-Fingerprinting for LLMs via Pseudo-random Sequences

arXiv:2606.03330v1 Announce Type: cross Abstract: Literature reveals that a Large Language Model's (LLM) behavior is not only conditioned by its original weights but also its instance-level parameters

FlowGuard: Flow Matching for Identity-Independent Detection of Data-Free Model Stealing Attacks on Energy System Intrusion Detection Systems

arXiv:2606.03430v1 Announce Type: cross Abstract: Artificial Intelligence (AI)-based Intrusion Detection Systems (IDS) deployed in energy infrastructure are vulnerable to model theft attacks, which al

From Non-Convex to Strongly Convex: Curvature-Adaptive FTPL for Online Optimization

arXiv:2606.02948v1 Announce Type: new Abstract: Curvature adaptivity is a classical theme in online optimization: for convex Lipschitz losses, adaptive methods interpolate between the optimal O(sqrt{T

From None to All: Self-Supervised 3D Reconstruction via Novel View Synthesis

arXiv:2603.27455v2 Announce Type: replace Abstract: In this paper, we introduce NAS3R, a self-supervised feed-forward framework that jointly learns explicit 3D geometry and camera parameters with no g

FSA-GRPO: Teaching Auditory LLMs to Use Few-shot Demonstrations

arXiv:2606.02615v1 Announce Type: cross Abstract: Few-shot prompting provides an effective way to adapt auditory large language models to low-resource tasks such as children's speech recognition. Howe

GARDEN: Gravity-Aligned Reconstruction of Disentangled ENvironments from RGB images

arXiv:2606.03921v1 Announce Type: new Abstract: Converting multi-view RGB observations into simulation-ready 3D environments remains challenging because current reconstruction pipelines produce monoli

Geometric Adaptive Control for a Quadrotor UAV with Wind Disturbance Rejection

arXiv:1803.06363v2 Announce Type: cross Abstract: This paper presents a geometric adaptive control scheme for a quadrotor unmanned aerial vehicle, where the effects of unknown, unstructured disturbanc

Geometric Adaptive Control with Neural Networks for a Quadrotor UAV in Wind fields

arXiv:1903.02091v1 Announce Type: cross Abstract: This paper proposes a geometric adaptive controller for a quadrotor unmanned aerial vehicle with artificial neural networks. It is assumed that the dy

GeoSem-WAM: Geometry- and Semantic-Aware World Action Models

arXiv:2606.03188v1 Announce Type: new Abstract: Recent World Action Models (WAMs) have demonstrated impressive capabilities in embodied decision-making. However, whether their effectiveness stems from

Graph Mamba Survival Analysis Based on Topology-Aware ordering

arXiv:2606.02602v1 Announce Type: cross Abstract: In computational pathology, Whole Slide Images (WSIs) survival analysis is crucial for patient prognosis assessment, but it faces multiple technical c

Greed is Good: A Unifying Perspective on Guided Generation

arXiv:2502.08006v3 Announce Type: replace-cross Abstract: Training-free guided generation is a widely used and powerful technique that allows the end user to exert further control over the generative

GuidedBridge: Training-freely Improving Bridge Models with Prior Guidance

arXiv:2606.03119v1 Announce Type: cross Abstract: Guidance methods, such as classifier-free guidance (CFG) and auto-guidance (AG), have advanced noise-to-data generation in diffusion models. Recently,

Hand Trajectory Fusion for Egocentric Natural Language Query Grounding

arXiv:2606.02962v1 Announce Type: cross Abstract: Egocentric Natural Language Query (NLQ) grounding asks a model to localize, in a long first-person video, the temporal interval that answers a free-fo

Hierarchies of Calibration: Classification meets Regression

arXiv:2606.03245v1 Announce Type: cross Abstract: Concepts of calibration formalize the compatibility between probabilistic predictions and the respective outcomes. In a nutshell, the outcomes ought t

High-Precision APT Malware Attribution with Out-of-Scope Resilience

arXiv:2606.03523v1 Announce Type: cross Abstract: Early attribution of Advanced Persistent Threat (APT) activity can help defenders prioritise investigation, select countermeasures, and reduce the imp

How Much of a Model Do We Need? Redundancy and Slimmability in Remote Sensing Foundation Models

arXiv:2601.22841v2 Announce Type: replace Abstract: Large-scale foundation models (FMs) in remote sensing (RS) (denoted as RS FMs) are developed following paradigms established in computer vision (CV)

How virtual power plants could provide energy for data centers

Would you take a payment to ramp down your electricity use? Would it change anything if you were doing so to help power a local data center? Google just signed a new deal to help pay for a virtual pow

researchmit-tech-review

How Visible Are Silent Manipulation Failures? An Observability Study of False-Success Detection in Simulated Robot Episodes

arXiv:2606.03134v1 Announce Type: cross Abstract: Imitation-learning policies for robot manipulation inherit the quality of the success labels attached to their training episodes, and those labels are

Human2Humanoid: Physics-Aware Cross-Morphology Motion Retargeting for Humanoid Robots

arXiv:2606.03476v1 Announce Type: new Abstract: Retargeting human motion to humanoid robots is critical for teleoperation, imitation learning and human-robot interaction. However, it remains challengi

Humanoid-GPT: Scaling Data and Structure for Zero-Shot Motion Tracking

arXiv:2606.03985v1 Announce Type: cross Abstract: We introduce Humanoid-GPT, a GPT-style Transformer with causal attention trained on a billion-scale motion corpus for whole-body control. Unlike prior

HybridThinker: Efficient Chain-of-Thought Reasoning via Compressed Memory and Transient Thought Steps

arXiv:2606.03768v1 Announce Type: new Abstract: Extended chain-of-thought (CoT) traces improve LLM reasoning but incur substantial computational and memory costs. While existing CoT compression method

IdEst: Assessing Self-Supervised Learning Representations via Intrinsic Dimension

arXiv:2606.03338v1 Announce Type: cross Abstract: Self-supervised learning (SSL) has emerged as a powerful paradigm for learning meaningful representations from unlabeled data. However, the standard p

Imaginative Perception Tokens Enhance Spatial Reasoning in Multimodal Language Models

arXiv:2606.03988v1 Announce Type: new Abstract: Vision language models (VLMs) excel at many tasks but still struggle with spatial reasoning when critical information is not directly observable. Many s

Safety

'Important You should give me full credits!': Exploring Prompt Injection Attacks on LLM-Based Automatic Grading Systems

arXiv:2606.03090v1 Announce Type: cross Abstract: The emergence of large language models (LLMs) has significantly accelerated recent research on LLM-based automatic grading (AG) systems. Benefiting fr

safetyarxiv-cs-ai

Improved Postural Stability Using a Lightweight Semi-Active Soft Back Support Device Under Standing Perturbations

arXiv:2606.02928v1 Announce Type: new Abstract: Older adults are particularly susceptible to falls following perturbations during standing, such as forward loss of balance. Back support devices that a

Inverting the Generation Process of Denoising Diffusion Implicit Models: Empirical Evaluation and a Novel Method

arXiv:2606.03111v1 Announce Type: new Abstract: This paper studies the problem of inverting the DDIM image generation process to recover latent variables, particularly the initial noise map, from a ge

It seems there is an entirely different set of rules for Republicans and Democrats.

Yann LeCun's post suggests a perceived double standard in how political rules or standards are applied differently to Republicans versus Democrats. The statement implies inconsistent enforcement or tr

researchyann-lecun--x

KletterMix: Climbing Toward High-Quality German Pretraining Data

arXiv:2606.03773v1 Announce Type: new Abstract: High-quality pretraining data is a central ingredient in modern language models, but German-language resources remain far less developed than their Engl

KVarN: Variance-Normalized KV-Cache Quantization Mitigates Error Accumulation in Reasoning Tasks

arXiv:2606.03458v1 Announce Type: new Abstract: Test-time scaling is a powerful approach to obtain better reasoning in large language models, but it becomes memory-bottlenecked during long-horizon dec

Language Models Compare Quantities Using Number-specific and Unit-specific Heuristics

arXiv:2606.03982v1 Announce Type: new Abstract: Quantities with measurement units, such as 110 cm and 1.2 m, require language models (LMs) to combine a numeral with a symbolic unit scale. Here, we stu

Large Byte Model: Teaching Language Models About Compiled Code

arXiv:2606.02834v1 Announce Type: cross Abstract: Malware analysis starts with the raw bytes of an executable program, and tools to 'lift' these to higher-level representations, such as assembly, are

LatentChem: From Textual CoT to Latent Thinking in Chemical Reasoning

arXiv:2602.07075v5 Announce Type: replace-cross Abstract: Current chemical large language models (LLMs) predominantly rely on explicit Chain-of-Thought (CoT) to solve complex reasoning problems. Howev

Lean-GAP: A Dataset of Formalized Graduate Algebra Problems

arXiv:2606.02588v1 Announce Type: cross Abstract: We present Lean-GAP (Lean-Graduate Agebra Problems), 430 formalized graduate-level algebra problems from the textbook Abstract Algebra by Dummit and F

Learned Non-Maximum Suppression for 3D Object Detection

arXiv:2606.03568v1 Announce Type: cross Abstract: Post-processing is a critical stage in LiDAR-based 3D object detection, where dense and overlapping proposals must be filtered for compact and reliabl

Learning DNF through Generalized Fourier Representations

arXiv:2506.01075v2 Announce Type: replace-cross Abstract: The Boolean Fourier representation has been widely used in learning theory, particularly for learning Disjunctive Normal Form (DNF) under unif

Learning Multi-Scale Hypergraph for High-Order Brain Connectivity Analysis

arXiv:2606.03310v1 Announce Type: cross Abstract: Understanding complex interactions between brain regions is critical for early neurodegenerative disease classification such as Alzheimer's Disease (A

Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining

arXiv:2509.22468v2 Announce Type: replace-cross Abstract: High-quality molecular representations are essential for property prediction and molecular design, yet large labeled datasets remain scarce. W

Learning to Refine: Spectral-Decoupled Iterative Refinement Framework for Precipitation Nowcasting

arXiv:2606.02661v1 Announce Type: cross Abstract: Accurate precipitation nowcasting is vital for disaster mitigation, but deep learning methods face a key trade-off: regression models produce over-smo

Learning to Solve, Forgetting to Retain: Correct-Set Turnover in RLVR

arXiv:2606.03087v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) improves the ability of large language model, yet headline accuracy gains often conceal a hidden c

Lexicons and grammars for language processing: industrial or handcrafted products?

arXiv:2606.03412v1 Announce Type: new Abstract: During the recent years, the use of linguistic data for language processing increased progressively. Such data are now commonly called language resource

Limit Analysis of Graph Neural Networks with Wireless Conflict Graphs

arXiv:2606.03794v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) have emerged as a powerful tool for wireless resource allocation that leverages the underlying graph structure of communica

Linguistic Productivity in Large Language Models: Models Coerce, but do not Preempt

arXiv:2606.02953v1 Announce Type: new Abstract: Usage-based theories of grammars posit that creative productivity of the structures of language is both bolstered and constrained by two distinct freque

Link Prediction or Perdition: the Seeds of Instability in Knowledge Graph Embeddings

arXiv:2606.03365v1 Announce Type: new Abstract: Embedding models (KGEMs) constitute the main link prediction approach to complete knowledge graphs. Standard evaluation protocols emphasize rank-based m