Search: “research”

The Platonic Defense: Backdoor Defense for Self-Supervised Encoders in the Era of Large Scale Pre-training

arXiv:2606.29451v1 Announce Type: new Abstract: Self-supervised learning (SSL) pretrained models have become a dominant paradigm for visual representation learning, but they are vulnerable to backdoor

Research

The Speedup Paradox: Rethinking Inference Speed-Quality Trade-off in Embodied Tasks

DGX agent

arXiv:2606.28529v1 Announce Type: cross Abstract: Embodied foundation models have recently been widely used to improve robot generalization and task success rates. Previous works apply lossy efficient

researcharxiv-cs-ai

30 Jun 2026

The Surprising Effectiveness of Video Diffusion Models for Hand Motion Reconstruction

arXiv:2606.30308v1 Announce Type: new Abstract: 4D hand motion reconstruction from egocentric video is bottlenecked by clear limitations of existing methods: image-based pipelines depend on a detector

The Voronoi Bottleneck: Capacity-Aware Dense Retrieval for Product Search

arXiv:2606.28359v1 Announce Type: cross Abstract: Dense embedding retrieval compresses all relevance information into a single inner product, imposing a fundamental geometric limit -- the Voronoi Bott

ThinkProbe: Beyond Accuracy -- Structural Profiling of Open-Ended LLM Reasoning Traces via Non-Generative Thought Graphs

arXiv:2606.29067v1 Announce Type: new Abstract: We present ThinkProbe, a framework for structural analysis of LLM reasoning traces. ThinkProbe converts each trace into a Thought Graph a directed graph

To Reason or to Fabricate: Reasoning Without Shortcuts via Hint-Anchored Pairwise Aggregation

arXiv:2606.29481v1 Announce Type: cross Abstract: While reinforcement learning (RL) significantly enhances LLM reasoning, its efficacy is severely undermined by Pre-RL data overlap, where RL datasets

To Tab or Not to Tab: Measuring Critical Engagement in AI Code Completion Tools Using Behavioral Signals and Attention Checks

arXiv:2606.30549v1 Announce Type: cross Abstract: AI code completion tools, such as Github Copilot, provide students with code suggestions to help them write programs. However, recent qualitative stud

Towards Complete Causal Explanation with Expert Knowledge

arXiv:2407.07338v4 Announce Type: replace-cross Abstract: We study the problem of restricting a Markov equivalence class of maximal ancestral graphs (MAGs) to only those MAGs that contain certain edge

Towards Engineering Scaling Laws with Pretraining Data Composition

arXiv:2606.19781v2 Announce Type: replace-cross Abstract: Neural scaling laws describe how model performance improves as a power law in compute, model size, and dataset size. While well-established fo

Towards Evaluating Data Priors for Tabular Foundation Models

arXiv:2606.29241v1 Announce Type: new Abstract: Data-generating priors are a central component of tabular foundation models because they define the task distribution used during pretraining. However,

TRACE: A Concept Bottleneck Model for Longitudinal 3D Glioblastoma Response Assessment

arXiv:2606.30313v1 Announce Type: new Abstract: Longitudinal glioblastoma response assessment requires comparing subtle tumor changes across MRI time points using structured clinical criteria such as

TRACE: Temporal Relationship-Aware Conversational Entrainment Detection in Dyadic Speech

arXiv:2606.30543v1 Announce Type: cross Abstract: With the proliferation of speech AI agents, understanding emotional entrainment in conversational interaction has become increasingly important. Emoti

Transformer Architectures as Complete Bayes Processes: A Formal Proof in the Measure-Theoretic Kernel Framework

arXiv:2606.30440v1 Announce Type: cross Abstract: We present a complete formal proof that transformer architectures, when their internal update mechanisms satisfy a Bayes joint-distribution condition,

Transition-Aware best-of-N sampling for Longitudinal Chest X-ray Reports

arXiv:2606.28393v1 Announce Type: new Abstract: In longitudinal clinical practice, every chest X-ray is read in the context of the patients prior exam, and much of what the radiologist communicates is

Turn-Averaged SAEs for Feature Discovery and Long-Context Attribution

arXiv:2606.28548v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) have become a useful tool for extracting interpretable features in language models. However, standard SAE architectures opera

Two-Stage Prompt Optimization for Few-Shot Relation Extraction: From Reasoning-Guided Search to Gradient-Guided Refinement

arXiv:2606.29639v1 Announce Type: cross Abstract: Automatic prompt optimization is still underexplored for episodic few-shot relation extraction with smaller language models. We propose a two-stage fr

Uncertainty Estimation in Pathology Foundation Models via Deep Mutual Learning

arXiv:2606.30020v1 Announce Type: new Abstract: Pathology foundation models (PFMs) offer generalizable representations for whole-slide image (WSI) analysis, yet their clinical adoption remains limited

Understanding LLM Intervention Explanations in Multi-Party Human-Robot Interaction

arXiv:2606.29460v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly embedded in social robots to support natural group interactions, yet their role in complex multi-party set

researcharxiv-cs-ro

UniPR-3D: Towards Universal Visual Place Recognition with Visual Geometry Grounded Transformer

arXiv:2512.21078v3 Announce Type: replace Abstract: Visual Place Recognition (VPR) has been traditionally formulated as a single-image retrieval task. Using multiple views offers clear advantages, yet

UniTriSplat: A Unified 3D Gaussian Splatting Framework with Uniform Spherical Rasterization for Universal Cameras

arXiv:2606.29794v1 Announce Type: new Abstract: Existing 3D Gaussian Splatting (3DGS) frameworks rely on camera-specific rasterization, suffering from inconsistent solid-angle sampling and degraded pe

UniVAD v2: Unified Visual Anomaly Detection via Support-Conditioned Boundary Construction

arXiv:2606.29714v1 Announce Type: new Abstract: Unified visual anomaly detection seeks to train a single detector that can be deployed across categories, domains, and application scenarios. In the few

Universality of empirical risk minimization

arXiv:2202.08832v3 Announce Type: replace-cross Abstract: We study a general class of optimization problems with decision variable oldsymbol{Theta} in R^{p imes k} and cost function which is the sum o

Variance Reduction for Stochastic Gradient Generalized Non-reversible Langevin Monte Carlo Algorithms

arXiv:2606.28808v1 Announce Type: cross Abstract: We study the leading-order fluctuation of stochastic gradient Euler-Maruyama estimators for generalized non-reversible Langevin dynamics. Under struct

VIB-AVSR: Variational Information Bottleneck for Noise-Robust LLM-Based Audio-Visual Speech Recognition

arXiv:2606.29632v1 Announce Type: cross Abstract: Audio-Visual Speech Recognition takes two input modalities, acoustic and visual streams, where visual information from lip movements aids recognition

ViewSplat: View-Adaptive 3D Gaussian Splatting for Feed-Forward Synthesis

arXiv:2603.25265v2 Announce Type: replace Abstract: We present ViewSplat, a view-adaptive 3D Gaussian splatting network for novel view synthesis from unposed images. While recent feed-forward 3D Gauss

Virtual Ring Try-On

arXiv:2606.28792v1 Announce Type: new Abstract: This paper presents an innovative approach that enables the users to capture their hand and try the jewel ring on their hand. The user captures the imag

W4A4 Quantization for Inference on Wan2.2-I2V-A14B

arXiv:2606.29337v1 Announce Type: new Abstract: We summarize our submission to Sub-Challenge 1: W4A4 Quantization for Inference (HiF4 / MXFP4) of the ICME 2026 Low-Bit-width Large-Model Quantization C

Warm-Starting Iterative Gaussian Processes for Faster Sequential Inference

arXiv:2511.16340v2 Announce Type: replace Abstract: Efficient Gaussian process (GP) inference is critical for sequential decision-making tasks such as active learning, online prediction, and Bayesian

Wasserstein Distributionally Robust Regret Optimization

arXiv:2504.10796v4 Announce Type: replace-cross Abstract: Distributionally robust optimization (DRO) is widely used for decision-making under uncertainty, but its adversarial focus on worst-case loss

We can finally say AI isn't killing jobs. A new paper from me, @tryramp, and @RevelioLabs uses firm-level spend and workforce data across 21…

We can finally say AI isn't killing jobs. A new paper from me, @tryramp, and @RevelioLabs uses firm-level spend and workforce data across 21K U.S. businesses to measure AI's impact on jobs. Firms that

researchyann-lecun--x

Weak Dominant Balance for Robust Identification of Dynamically Consistent Fluid Flow Structure

arXiv:2606.29047v1 Announce Type: cross Abstract: Extracting interpretable, localized physical mechanisms from complex spatiotemporal data is a foundational challenge across physics, biology, and engi

Weighted Contrastive Learning for Anomaly-Aware Time-Series Forecasting

arXiv:2512.07569v2 Announce Type: replace-cross Abstract: Reliable forecasting of multivariate time series under anomalous conditions is crucial in applications such as ATM cash logistics, where sudde

We're coming out of stealth. We've built our first racks after a successful A0 tapeout, 1B+ in customer contracts, and 800m raised. Early …

We're coming out of stealth. We've built our first racks after a successful A0 tapeout, 1B+ in customer contracts, and 800m raised. Early customer tests show us achieving SOTA throughput, latency, and

researchkarpathy--x

What Color is the Sky (for a non-human) ?

arXiv:2606.28912v1 Announce Type: new Abstract: The light of the daytime sky contains a mixture of many colors yet is perceived as blue by human observers. This is largely due to the particular respon

When Can Conformal Risk Control Certify LLM Outputs? Bounds, Impossibility, and Adaptation for Structured Generation

arXiv:2606.29054v1 Announce Type: new Abstract: Large language models (LLMs) deployed for structured generation (NER, JSON extraction, QA, and classification) lack formal reliability guarantees, and s

When Does Sparsity Mitigate the Curse of Depth in LLMs

arXiv:2603.15389v2 Announce Type: replace Abstract: Recent work has demonstrated the curse of depth in large language models (LLMs), where later layers contribute less to learning and representation t

When Does Synthetic CT Transfer? A Label-Free Donor/Host Diagnostic for Medical Vision-Language Model Routing on Real Lung CT

arXiv:2606.29232v1 Announce Type: new Abstract: A synthetic measurement of model competence is useful only if it survives the move to real data, yet the real labels that would verify it are exactly wh

When May I Help You? On The Effect of Proactivity on Group Human-Robot Collaboration

arXiv:2606.28469v1 Announce Type: new Abstract: Robot initiative is a central challenge in multi-party human-robot collaboration. A robot that contributes without being addressed may provide timely su

researcharxiv-cs-ro

When Prices Double in a Week: Forecasting of Agricultural Volatility in Import-Isolated Markets

arXiv:2606.29248v1 Announce Type: new Abstract: Vegetable prices in Sri Lanka are highly volatile because the market is largely import-isolated, so supply disruptions quickly drive prices up. This stu

Where Do Humans Look When Demonstrating to Robots? Human Gaze Behavior in Pick-and-Place Tasks Across Demonstration Devices

arXiv:2506.05808v2 Announce Type: replace Abstract: Imitation learning for generalizable performance often requires a large volume of demonstration data, making the process significantly costly. One p

researcharxiv-cs-ro

Which Tokens Need Context? A Reference-Based Analysis of Translation Responsibility Using Fertility and Entropy

arXiv:2606.29489v1 Announce Type: new Abstract: When humans translate, not every word depends equally on the surrounding context. Some tokens, particularly function words like pronouns and auxiliaries

Wireless Backdoor Attack and Defense for Semantic Communications over Multiple Access Channel

arXiv:2606.30595v1 Announce Type: cross Abstract: Semantic communication (SemCom) aims to preserve semantic meaning and task-oriented information beyond conventional message recovery over wireless cha

A Gaussian Perspective for Distributional Discrepancy in Generative Diffusion Models

arXiv:2601.13602v3 Announce Type: replace-cross Abstract: This paper introduces an analytical approach to quantifying and optimizing the distributional discrepancy in generative diffusion models. For

A Primer on SO(3) Action Representations in Deep Reinforcement Learning

arXiv:2510.11103v3 Announce Type: replace-cross Abstract: Many robotic control tasks require policies to act on orientations, yet the geometry of SO(3) makes this nontrivial. Because SO(3) admits no g

A Study of Temporal Fusion Strategies for Named Entity Recognition in Historical Texts

arXiv:2606.27881v1 Announce Type: cross Abstract: Temporal variation poses a unique challenge for named entity recognition (NER) in historical texts, where entities drift in surface form and salience

A Survey of Automated Presentation Coaching: Systems, Methods, and Open Challenges

arXiv:2606.27380v1 Announce Type: new Abstract: Automated coaching for oral presentations sits at the intersection of computer-assisted pronunciation training (CAPT), prosody modeling, and speech synt

A very damaged man who had the political power and the private wealth to save millions of lives but chose instead to allow suffering & death…

A very damaged man who had the political power and the private wealth to save millions of lives but chose instead to allow suffering & death. Not only that, he uses his influence to sow ethnic and rel

researchyann-lecun--x

Accelerating Hierarchical Sparse Predictive Coding with Hybrid Amortized Inference

arXiv:2606.27802v1 Announce Type: new Abstract: Hierarchical predictive coding provides an interpretable framework for perception as error-driven inference in multi-layer generative models, while spar