research

Time-Warping Recurrent Neural Networks for Transfer Learning

arXiv:2604.02474v2 Announce Type: replace Abstract: Dynamical systems describe how a physical system evolves over time. Physical processes can evolve faster or slower in different environmental condit

TinySSL: Distilled Self-Supervised Pretraining for Sub-Megabyte MCU Models

DGX agent

arXiv:2605.08241v1 Announce Type: cross Abstract: Self-supervised learning (SSL) has transformed representation learning for large models, yet remains unexplored for microcontroller (MCU)-class models

researcharxiv-cs-ai

12 May 2026

Top-H Decoding: Adapting the Creativity and Coherence with Bounded Entropy in Text Generation

arXiv:2509.02510v2 Announce Type: replace-cross Abstract: Large language models (LLMs), despite their impressive performance across a wide range of tasks, often struggle to balance two competing objec

TopoGeoScore: A Self-Supervised Source-Only Geometric Framework for OOD Checkpoint Selection

arXiv:2605.08870v1 Announce Type: new Abstract: Out-of-distribution (OOD) robustness is difficult to diagnose when target-domain labels are unavailable. We consider a more restrictive source-only vari

TopoU-Net: a U-Net architecture for topological domains

arXiv:2605.10091v1 Announce Type: new Abstract: Many modern datasets mix points, edges, regions, groups, objects, events, hyperedges, and relations. Yet neural architectures often force such data into

Toward an Engineering of Science: Rebalancing Generation and Verification in the Age of AI

arXiv:2605.10425v1 Announce Type: cross Abstract: AI systems can now cheaply generate plausible scientific artifacts such as papers, reviews, and surveys. This creates a risk of epistemic pollution in

Toward Optimal Regret in Robust Pricing: Decoupling Corruption and Time

arXiv:2605.08290v1 Announce Type: cross Abstract: We design the first regret guarantees for robust dynamic pricing that decouple the dependence on the corruption C and the time horizon T. In dynamic p

Towards a Certificate of Trust: Task-Aware OOD Detection for Scientific AI

arXiv:2509.25080v3 Announce Type: replace Abstract: Data-driven models are increasingly adopted in critical scientific fields like weather forecasting and fluid dynamics. These methods can fail on out

Towards Backdoor-Based Ownership Verification for Vision-Language-Action Models

arXiv:2605.09005v1 Announce Type: cross Abstract: Vision-Language-Action models (VLAs) support generalist robotic control by enabling end-to-end decision policies directly from multi-modal inputs. As

Towards Effective Theory of LLMs: A Representation Learning Approach

arXiv:2605.09294v1 Announce Type: cross Abstract: We propose Representational Effective Theory (RET), a framework for describing large language model computation in terms of learned macrostates rather

Towards Interpretable Damage Detection based on Aerodynamic Pressure Measurements

arXiv:2605.08187v1 Announce Type: cross Abstract: The increasing flexibility of modern large wind turbine blades necessitates cost-efficient and reliable structural monitoring solutions. For this purp

Training Reasoning Models on Saturated Problems via Failure-Prefix Conditioning

arXiv:2601.20829v2 Announce Type: replace-cross Abstract: As Reinforcement Learning with Verifiable Rewards (RLVR) substantially improves the reasoning abilities of large language models (LLMs), a new

TRAM: Training Approximate Multiplier Structures for Low-Power AI Accelerators

arXiv:2605.08231v1 Announce Type: cross Abstract: Reducing power consumption in AI accelerators is increasingly important. Approximate computing can reduce power consumption while keeping the accuracy

Transfer Learning for Dead Fuel Moisture Prediction Using Time-Warping Recurrent Neural Networks

arXiv:2605.08379v1 Announce Type: cross Abstract: This paper proposes a time-warping transfer learning method, a technique for temporally rescaling the learned dynamics of a recurrent neural network (

Transformers Can Implement Preconditioned Richardson Iteration for In-Context Gaussian Kernel Regression

arXiv:2605.08475v1 Announce Type: cross Abstract: Mechanistic accounts of in-context learning (ICL) have identified iterative algorithms for linear regression and related linear prediction tasks, ofte

Transforming the Use of Earth Observation Data: Exascale Training of a Generative Compression Model with Historical Priors for up to 10,000x Data Reduction

arXiv:2605.08633v1 Announce Type: cross Abstract: Earth observation is becoming one of the largest data-producing activities in science, yet current pipelines still treat compression as a storage and

Trapping Attacker in Dilemma: Examining Internal Correlations and External Influences of Trigger for Defending GNN Backdoors

arXiv:2605.08278v1 Announce Type: cross Abstract: GNNs have become a standard tool for learning on relational data, yet they remain highly vulnerable to backdoor attacks. Prior defenses often depend o

Trump had one of his worst mental health episodes yet last night, posting over 55 times in 3 hours. Here is the list: 10:15 PM - Accuses Oba…

Trump had one of his worst mental health episodes yet last night, posting over 55 times in 3 hours. Here is the list: 10:15 PM - Accuses Obama of attempting a coup in 2016 10:15 PM - Says Obama worked

researchyann-lecun--x

Turbo-GS: Accelerating 3D Gaussian Fitting for High-Quality Radiance Fields

arXiv:2412.13547v3 Announce Type: replace Abstract: Novel-view synthesis plays a crucial role in computer vision with applications in 3D reconstruction, mixed reality, and robotics. Recent approaches,

UIESNN: A Scale-Aware Spiking Network for Underwater Image Enhancement

arXiv:2605.08376v1 Announce Type: new Abstract: Underwater image enhancement (UIE) is a practically important yet underexplored application of spiking neural networks (SNNs), where the dominant degrad

UM-Text: A Unified Multimodal Model for Image Understanding and Visual Text Editing

arXiv:2601.08321v3 Announce Type: replace Abstract: With the rapid advancement of image generation, visual text editing using natural language instructions has received increasing attention. The main

Uncertainty-Aware Token Importance Estimation in Spiking Transformers

arXiv:2605.09276v1 Announce Type: cross Abstract: Spiking transformers have shown strong potential for neuromorphic vision, yet their token processing across multiple spiking steps still introduces su

Uncertainty Estimation for Heterophilic Graphs Through the Lens of Information Theory

arXiv:2505.22152v2 Announce Type: replace Abstract: While uncertainty estimation for graphs recently gained traction, most methods rely on homophily and deteriorate in heterophilic settings. We addres

Uncertainty-Guided Dual-Domain Learning for Reliable Skin Lesion Segmentation

arXiv:2605.09600v1 Announce Type: cross Abstract: Accurate skin lesion segmentation is vital for dermoscopic Computer-Aided Diagnosis. However, visual ambiguity and morphological irregularity often de

Uncovering Intra-expert Activation Sparsity for Efficient Mixture-of-Expert Model Execution

arXiv:2605.08575v1 Announce Type: cross Abstract: Mixture of Experts (MoE) architecture has become the standard for state-of-the-art large language models, owing to its computational efficiency throug

Unified Approach for Weakly Supervised Multicalibration

arXiv:2605.09857v1 Announce Type: cross Abstract: Multicalibration requires predicted scores to agree with label probabilities across rich families of subgroups and score-dependent tests, but existing

Unifying Perspectives: Plausible Counterfactual Explanations on Global, Group-wise, and Local Levels

arXiv:2405.17642v3 Announce Type: replace-cross Abstract: The growing complexity of AI systems has intensified the need for transparency through Explainable AI (XAI). Counterfactual explanations (CFs)

Universal Feature Selection with Noisy Observations and Weak Symmetry Conditions

arXiv:2605.09396v1 Announce Type: cross Abstract: This paper relaxes the restrictive symmetry conditions adopted in [4], [5] and extends their universal feature selection framework to accommodate nois

Useful for Exploration, Risky for Precision: Evaluating AI Tools in Academic Research

arXiv:2605.10125v1 Announce Type: new Abstract: Artificial intelligence (AI) tools are being incorporated into scientific research workflows with the potential to enhance efficiency in tasks such as d

UxSID: Semantic-Aware User Interests Modeling for Ultra-Long Sequence

arXiv:2605.09040v1 Announce Type: new Abstract: Modeling ultra-long user sequences involves a difficult trade-off between efficiency and effectiveness. While current paradigms rely on either item-spec

Verbalized Algorithms: Classical Algorithms are All You Need (Mostly)

arXiv:2509.08150v5 Announce Type: replace Abstract: Reasoning is a fundamentally algorithmic task. Yet current work on LLM-based reasoning relies on free-form generation whose theoretical guarantees (

researcharxiv-cs-cl

Virtual Personas for Language Models via an Anthology of Backstories

arXiv:2407.06576v4 Announce Type: replace-cross Abstract: Large language models (LLMs) are trained from vast repositories of text authored by millions of distinct authors, reflecting an enormous diver

Visual Hand Gesture Recognition with Deep Learning: A Comprehensive Review of Methods, Datasets, Challenges and Future Research Directions

arXiv:2507.04465v4 Announce Type: replace Abstract: The rapid evolution of deep learning (DL) models and the ever-increasing size of available datasets have raised the interest of the research communi

ViSurf: Visual Supervised-and-Reinforcement Fine-Tuning for Large Vision-and-Language Models

arXiv:2510.10606v4 Announce Type: replace Abstract: Post-training Large Vision-and-Language Models (LVLMs) typically involves Supervised Fine-Tuning (SFT) for knowledge injection or Reinforcement Lear

VPD-100K: Towards Generalizable and Fine-grained Visual Privacy Protection

arXiv:2605.10229v1 Announce Type: new Abstract: Privacy protection has become a critical requirement in the era of ubiquitous visual data sharing, imposing higher demands on efficient and robust priva

VRA: Grounding Discrete-Time Joint Acceleration in Voltage-Constrained Actuation

arXiv:2605.10696v1 Announce Type: new Abstract: Discrete-time joint acceleration constraints are widely used to enforce position and velocity limits. However, under voltage-constrained electric actuat

researcharxiv-cs-ro

Watermarking Graph Neural Networks via Explanations for Ownership Protection

arXiv:2501.05614v2 Announce Type: replace-cross Abstract: Graph Neural Networks (GNNs) are widely deployed in industry, making their intellectual property valuable. However, protecting GNNs from unaut

Weighted Rules under the Stable Model Semantics

arXiv:2605.09519v1 Announce Type: new Abstract: We introduce the concept of weighted rules under the stable model semantics following the log-linear models of Markov Logic. This provides versatile met

What Concepts Lie Within? Detecting and Suppressing Risky Content in Diffusion Transformers

arXiv:2605.10180v1 Announce Type: new Abstract: The rise of text-to-image (T2I) models has increasingly raised concerns regarding the generation of risky content, such as sexual, violent, and copyrigh

What Does Flow Matching Bring To TD Learning?

arXiv:2603.04333v2 Announce Type: replace-cross Abstract: Recent work shows that flow matching can be effective for scalar Q-value function estimation in reinforcement learning (RL), but it remains un

When AI Meets Science: Research Diversity, Interdisciplinarity, Visibility, and Retractions across Disciplines in a Global Surge

arXiv:2605.06033v2 Announce Type: replace-cross Abstract: The extent to which Artificial Intelligence (AI) can trigger generalized paradigm shifts in science is unclear. Although some of these technol

When and Why Grouping Attention Heads Accelerates Muon Optimization

arXiv:2605.08933v1 Announce Type: new Abstract: Muon orthogonalizes matrix updates, but multi-head attention naturally operates at the level of heads. This granularity mismatch raises the question of

When Can Human-AI Teams Outperform Individuals? Tight Bounds with Impossibility Guarantees

arXiv:2605.08710v1 Announce Type: new Abstract: Human-AI teams fail to outperform their best member in 70% of studies, yet no theory specifies when complementarity is achievable. We derive tight bound

When Does Value-Aware KV Eviction Help? A Fixed-Contract Diagnostic for Non-Monotone Cache Compression

arXiv:2605.08234v1 Announce Type: cross Abstract: Long-context LLM inference is bottlenecked by the memory and bandwidth cost of reading large KV caches during decoding. KV compression reduces this co

When Efficient Communication Explains Convexity

arXiv:2602.02821v2 Announce Type: replace Abstract: Much recent work has argued that the variation in the languages of the world can be explained from the perspective of efficient communication; in pa

researcharxiv-cs-cl

When Few Steps Are Enough: Training-Free Acceleration of Identity-Preserved Generation

arXiv:2605.09460v1 Announce Type: cross Abstract: Identity-preserved image generation is typically built on many-step diffusion backbones, making personalized generation expensive at deployment time.

When Less is More: The LLM Scaling Paradox in Context Compression

arXiv:2602.09789v3 Announce Type: replace Abstract: Scaling up model parameters has long been a prevalent training paradigm driven by the assumption that larger models yield superior generation capabi

When Style Similarity Scores Fail: Diagnosing Raw CSD Cosine in Artist-Style Evaluation

arXiv:2605.09030v1 Announce Type: new Abstract: Raw cosine in the 768-dimensional output space of the Contrastive Style Descriptor (CSD) is now widely read as an absolute, calibrated style-fidelity sc