Search: “research”

Contrastive ESA: Human Evaluation of Multiple Translations at Once

arXiv:2607.26640v1 Announce Type: new Abstract: Current human evaluation of machine translation typically assesses single outputs in isolation, a paradigm that suffers from high annotator noise and co

Convex Collision-Free Regions

arXiv:2607.26901v1 Announce Type: cross Abstract: Convex Collision-Free Regions (CCFR) is a collision handling method that explicitly represents local convex feasible regions to enforce non-penetratio

researcharxiv-cs-ro

30 Jul 2026

Deep Expert Injection for Anchoring Retinal VLMs with Domain-Specific Knowledge

arXiv:2603.07131v4 Announce Type: replace Abstract: Large Vision Language Models (LVLMs) show immense potential for automated ophthalmic diagnosis. However, their clinical deployment is severely hinde

Denoising growth complexity: Data geometry and certified schedules for diffusion sampling

arXiv:2607.26285v1 Announce Type: cross Abstract: Two central challenges in diffusion-based sampling are the theoretical one of understanding their remarkable effectiveness even in high-dimensional se

Dense Local Dependencies Induce Attention-Logit Explosion and Training Instability During Long-Sequence Transformer Training

arXiv:2505.15548v2 Announce Type: replace Abstract: Autoregressive transformer language models frequently exhibit training instability when trained on long sequences, particularly under low-precision

Dense Soft Weighting for Radar Ego-Velocity Estimation

arXiv:2607.26980v1 Announce Type: new Abstract: Sensing ego-velocity estimation is fundamental to state estimation in visually degraded environments, where camera- and LiDAR-based pipelines can become

Detecting seizure onset and offset times using human intelligence: A critical-transitions-based approach

arXiv:2607.27105v1 Announce Type: cross Abstract: Most existing seizure detection algorithms require extensive pre-processing of the data and rely on heuristic or currently unexplainable machine learn

Dice Loss for Data-imbalanced NLP Tasks

arXiv:1911.02855v5 Announce Type: replace Abstract: Many NLP tasks such as tagging and machine reading comprehension are faced with the severe data imbalance issue: negative examples significantly out

Dissecting Sensitivity to Training Language in Self-Supervised Speech Learning Using Neural Audio Codec Tokens

arXiv:2607.26350v1 Announce Type: cross Abstract: Neural audio codecs (NACs) have become popular for obtaining speech representations as discrete tokens. Beyond compression, discrete tokens can be use

Domain adaptation for handwriting trajectory reconstruction from IMU sensors

arXiv:2607.26736v1 Announce Type: new Abstract: Digital pens are commonly used to write on digital devices, providing the handwriting trace and enhancing human-computer interation. This study focuses

DP-MGTD: Privacy-Preserving Machine-Generated Text Detection via Adaptive Differentially Private Entity Sanitization

arXiv:2601.04641v2 Announce Type: replace-cross Abstract: The deployment of Machine-Generated Text (MGT) detection systems necessitates processing sensitive user data, creating a fundamental conflict

DuplexGen: Adaptive Synthesis of Human-AI Turn-Taking Dialogues

arXiv:2607.26178v1 Announce Type: new Abstract: Turn-taking is a central component of full-duplex interaction. Which turn-taking behaviors are appropriate varies with the scenario, yet current models

Dynamic Parameterization Is Not Dynamic Inference

arXiv:2607.26192v1 Announce Type: new Abstract: Input-dependent controller coefficients are often treated as evidence of dynamic inference or computational savings. This interpretation conflates three

Efficient Heteroscedastic Bayesian Optimization for Risk-Aware AutoRL

arXiv:2607.26680v1 Announce Type: new Abstract: Reinforcement learning (RL) has shown remarkable success across a wide range of complex tasks. However, RL outcomes can be highly stochastic, and both e

Emergent Sparsity in Frozen Random CNN Feature Extractors for Deep Reinforcement Learning

arXiv:2607.26059v1 Announce Type: new Abstract: We report a striking phenomenon: deep reinforcement learning agents trained with frozen, randomly initialized CNN feature extractors spontaneously devel

Enfold: Folding World-Generator Computation into Predictive Representations for Efficient Embodied Control

arXiv:2607.26657v1 Announce Type: new Abstract: World generative models are typically used through what they produce: a rendered future, a video-conditioned action, or latent context computed by a cos

Entity Resolution in Practice: Lessons from a Self-Serve Pipeline

arXiv:2607.26298v1 Announce Type: new Abstract: We built and evaluated a self-serve entity resolution (ER) system on six benchmarks spanning 864 to 5M records, and three lessons emerged that are absen

Equilibrium Training of Energy-Based Models with Parallel Trajectory Tempering

arXiv:2607.27077v1 Announce Type: new Abstract: Energy-Based Models (EBMs) provide an interpretable framework for generative modeling of scientific data, but poor Markov Chain Monte Carlo mixing often

Examining the Efficacy of Graph Neural Network Message-Passing in Regression Contexts

arXiv:2607.26404v1 Announce Type: new Abstract: Graph Neural Networks (GNN) facilitate effective prediction on graph data such as molecules, media networks and neural network blueprints. GNNs facilita

Existence-Field Diffusion Model for Spatial Point Processes with Variable Cardinality

arXiv:2607.26428v1 Announce Type: new Abstract: We study generative modeling of spatial point processes (SPP), where both the number of points and their spatial configuration are governed by a joint d

Feature Bagging Provides Stability

arXiv:2607.26964v1 Announce Type: cross Abstract: We study feature bagging through the lens of algorithmic stability. Feature bagging is an ensemble strategy that aggregates base learners trained on r

Few-Shot Open-Set Audio Classification via Transductive Prototype Refinement and Class Logit Enhancement

arXiv:2607.26607v1 Announce Type: cross Abstract: Few-shot Open-set audio classification requires classifying query samples from known classes with a few labeled support samples while rejecting query

Field Codes for Distributed Coupling Samplers and Certified Empirical Transport

arXiv:2607.27078v1 Announce Type: cross Abstract: In this paper, we formulate three communication tasks for empirical optimal transport: distributed coupling sampling, cost-evaluable coupling output,

FloDR: An invertible dimensionality reduction method based on a normalising flow

arXiv:2607.26278v1 Announce Type: new Abstract: It is common for two-dimensional embeddings of high-dimensional data to be read far beyond what they can support. Distances in and between clusters, the

FreeShadow: Training-Free Shadow Removal via Illumination Transfer and Selective Content Preservation in Diffusion Models

arXiv:2607.26715v1 Announce Type: new Abstract: Existing supervised and unsupervised shadow removal methods often suffer from limited generalization due to the insufficient diversity of available trai

FreqForcing: Autoregressive Long Video Generation via Spectral Self-Anchoring

arXiv:2607.27110v1 Announce Type: new Abstract: Autoregressive video diffusion models enable real-time streaming video generation. However, errors introduced during self-rollout accumulate over long h

From Spatial Semantics to Temporal Context: Leveraging Gaze Trajectory for Weakly Supervised Medical Image Segmentation

arXiv:2607.26542v1 Announce Type: new Abstract: Medical image segmentation heavily depends on labor-intensive and time-consuming pixel-level annotations. Eye tracking offers a cost-effective solution

GBPP: Grasp-Aware Base Placement Prediction for Robots via Two-Stage Learning

arXiv:2509.11594v3 Announce Type: replace Abstract: GBPP is a fast learning based scorer that selects a robot base pose for grasping from a single RGB-D snapshot. The method uses a two stage curriculu

Generation or Judgement? A Paradigm Perspective on LLM-Based Emotion-Cause Pair Extraction in Conversation

arXiv:2607.26967v1 Announce Type: new Abstract: Emotion-cause pair extraction in conversation (ECPEC) identifies utterance pairs in which one utterance causes an emotion expressed in another. Recent L

Global Exponential Stabilization of the Kinematic Bicycle Model of a Car in Polar Coordinates

arXiv:2607.26442v1 Announce Type: cross Abstract: At parking speeds, the kinematic bicycle is the prevailing model for car-like vehicles. Yet, despite its wide use, stabilizing feedback laws for this

Global Sensitive-Based Input Shaping for UAV-Payload Precision Motion Control

arXiv:2607.26717v1 Announce Type: cross Abstract: This work presents a comprehensive analysis and design of global sensitivity-based input shapers for a 3D Unmanned Aerial Vehicle-payload system, emph

GPTQ-2D: Cubic-Time Two-Sided Adaptive Rounding

arXiv:2607.27042v1 Announce Type: cross Abstract: Adaptive rounding methods such as GPTQ, or equivalently Babai's nearest plane algorithm, round a real matrix to integers under a quadratic metric. The

Harnessing Large Language Models for Intelligent Resource Allocation in the Internet of Everything

arXiv:2607.26602v1 Announce Type: cross Abstract: The rapid development of the Internet of Everything (IoE) is accelerating the adoption of intelligent applications. However, the massive number of con

HERMES: A Hybrid Ensemble for Head-and-Neck Tumor Segmentation, TN Staging, and Recurrence-Free Survival on PET/CT

arXiv:2607.26498v1 Announce Type: new Abstract: We present HERMES (Hybrid Ensemble for Radiotherapy-target segmentation, Malignancy staging, and Event-free Survival), a single containerized algorithm

High-Order Markov Blanket Discovery via a k-Order Relaxation of the Faithfulness Assumption

arXiv:2607.26357v1 Announce Type: new Abstract: The problem of learning the graphical Markov blanket (MB) of a variable from data has applications in many areas such as structure learning for Bayesian

Improving Knowledge Distillation Under Unknown Covariate Shift Through Confidence-Guided Data Augmentation

arXiv:2506.02294v3 Announce Type: replace Abstract: Large foundation models trained on extensive datasets demonstrate strong zero-shot capabilities in various domains. Knowledge distillation has becom

Incast-Free MoE Rate-Based Scheduling

arXiv:2607.26340v1 Announce Type: cross Abstract: Mixture of Experts (MoE) architectures have become key to large language models; however, their typical round-robin (RR) scheduling introduces signifi

Inkling-small. 2 weeks after inkling Nearly as good as Inkling but 4x smaller. We're just getting started...🔥

researchsoumith-chintala--x

Inkling-small. 2 weeks after inkling Nearly as good as Inkling but 4x smaller. We're just getting started...🔥 Today, we are releasing Inkling-Small. Inkling-Small achieves comparable performance to In

InkShield: Writing Style Protection Against Unauthorized Handwriting Mimicry

arXiv:2607.26976v1 Announce Type: cross Abstract: Recent handwritten text generators can reproduce a writer's style from publicly available references, posing risks of document forgery and identity mi

Interpretable Image-Level Acne Severity Grading via EfficientNet-B0 Transfer Learning and Grad-CAM

arXiv:2607.26461v1 Announce Type: new Abstract: Acne vulgaris affects most adolescents and many adults. Accurate severity grading guides treatment, monitoring, and clinical trial endpoints, but manual

Keyless Attention: Value-Space Routing and Value-Only Caching for Efficient Transformers

arXiv:2606.21848v2 Announce Type: replace Abstract: Transformer architectures form the foundation of modern natural language processing, making it crucial to address the efficiency and scalability lim

Kinetic Mining in Context: Few-Shot Action Synthesis via Text-to-Motion Distillation

arXiv:2512.11654v3 Announce Type: replace Abstract: The acquisition cost for large, annotated motion datasets remains a critical bottleneck for skeletal-based Human Activity Recognition (HAR). Althoug

Knowledge-guided Disentanglement with Atomic Actions for Action Recognition

arXiv:2607.26097v1 Announce Type: new Abstract: Action recognition in complex scenes often involves multiple concurrent fine-grained actions, making it challenging to model internal action structures.

Large Emotional World Model

arXiv:2512.24149v2 Announce Type: replace Abstract: The world is governed by both physical laws and affective dynamics. Physical laws govern state transitions, while affective dynamics shape human act

Learning Controlled Stochastic Differential Equations

arXiv:2411.01982v2 Announce Type: replace-cross Abstract: We study the problem of learning controlled stochastic differential equations (SDEs) [ dX_t = b(t,X_t,u_t),dt + sigma(t,X_t,u_t),dW_t, ] whose

Learning the Word Problem: Geodesic Lengths and Cryptographic Applications

arXiv:2607.26241v1 Announce Type: cross Abstract: The Word Problem has been a subject of intensive mathematical study for over a century, initially driving advances in combinatorial group theory and m

Linguistic Monoculture in LLM-Assisted Language Use

arXiv:2607.27134v1 Announce Type: cross Abstract: Writing and communication are increasingly mediated by large language models (LLMs) that are being used to draft, revise and polish text. Although suc

LISA-3D: Lifting Language-Image Segmentation to 3D via Multi-View Consistency

arXiv:2512.01008v2 Announce Type: replace Abstract: Text-driven 3D reconstruction requires masks that understand free-form instructions and remain stable under viewpoint changes. We present LISA-3D, a