research

PC-Edit: Prompt-Contrastive Region Discovery and Region-Guided Editing

arXiv:2607.21318v1 Announce Type: cross Abstract: Replacing an object with one that differs in category or shape requires complete source removal, natural target formation unconstrained by the source

PersonaGesture: Single-Reference Co-Speech Gesture Personalization for Unseen Speakers

DGX agent

arXiv:2605.06064v2 Announce Type: replace Abstract: We propose PersonaGesture, a diffusion-based pipeline for single-reference co-speech gesture personalization of unseen speakers. Given target speech

researcharxiv-cs-cv

24 Jul 2026

PhysCoRe: Physics-Corrected Residual World Models for Material-Aware Deformable Dynamics

arXiv:2607.20653v1 Announce Type: cross Abstract: Predicting how deformable objects evolve under robotic manipulation is a longstanding challenge. Existing approaches typically rely on per-object opti

Physics-Informed Deep Learning Model for Cross-Modality Super-Resolution in Fluorescence Microscopy

arXiv:2607.21190v1 Announce Type: new Abstract: Cross-modality image translation offers a route to super-resolution fluorescence microscopy from low-resolution images while reducing phototoxicity and

Pipelined Gradient Coding

arXiv:2607.20739v1 Announce Type: cross Abstract: In large-scale machine learning, distributed training commonly involves multiple workers evaluating the gradients of the model on different dataset pa

PlanE: Meta Planning of Data, Tuning, and Inference for Extractive-based LLMs

arXiv:2607.20470v1 Announce Type: new Abstract: Enhancing the task-specific capabilities of Large Language Models (LLMs) primarily requires substantial instruction-tuning datasets. However, the sheer

Position: Stop Reactively Patching Your Model Every Time and Start Proactive Test-Driven AI Development

arXiv:2607.20532v1 Announce Type: cross Abstract: Many modern AI systems are designed to operate under diverse, open-ended, use-cases. To help generalize deployed systems, many deployed-system mainten

Post-Hoc Reasoning in Chain of Thought: Decoding and Steering Pre-Committed Answers

arXiv:2603.01437v2 Announce Type: replace Abstract: As chain of thought (CoT) has become central to scaling reasoning capabilities in large language models (LLMs), it has also emerged as a promising t

Probabilistic Residual Learning for Online Recommendations

arXiv:2607.20863v1 Announce Type: cross Abstract: Modern recommender systems are typically based on deep learning (DL) models, where a dense encoder learns representations of users and items. As a res

Progressive Cramming: Reliable Token Compression and What It Reveals

arXiv:2607.21231v1 Announce Type: new Abstract: Token cramming compresses sequences into learned embeddings with near-perfect reconstruction, but fixed token budgets and 99% accuracy thresholds leave

Recurrent Sinusoidal INRs for Efficient High-Fidelity Representation

arXiv:2607.21485v1 Announce Type: new Abstract: We study sinusoidal recurrence as an iterative mechanism for harmonic spectral enrichment in implicit neural representations (INRs). Our analysis reveal

Representative Sets in Propositional Abduction

arXiv:2607.21183v1 Announce Type: cross Abstract: The propositional abduction problem is a well-known form of non-monotonic reasoning where we are asked to find an explanation of a given manifestation

Response drift across frontier large language models

arXiv:2607.20454v1 Announce Type: cross Abstract: All frontier large language models (LLMs) exhibit response drift -- producing outputs that deviate from expert-validated references -- yet the magnitu

Riemannian Deep Learning: Modules, Networks, and Geometries

arXiv:2607.19305v2 Announce Type: replace-cross Abstract: Deep neural networks on manifold-valued representations have attracted growing interest, but many basic components remain tied to specific man

Scientific exploration, collaboration and labor division in the large language model era

arXiv:2607.20923v1 Announce Type: cross Abstract: Large language models (LLMs) have rapidly and significantly entered scientific workflows, but it remains unclear how their diffusion is associated wit

Self-Supervised Bio-Inspired Robotic Trajectory Planning with Obstacle Avoidance

arXiv:2607.20743v1 Announce Type: cross Abstract: Trajectory planning is a fundamental problem in robotics, requiring the generation of collision-free and efficient trajectories in a potentially compl

Semantic-Aware Task Clustering for Constructive and Cooperative Multi-Tasking

arXiv:2607.21426v1 Announce Type: new Abstract: Cooperative multi-task semantic communication (CMT-SemCom) improves task execution performance by leveraging shared representations. However, as we demo

Semantic Field Theory: Historical Origin, Higher-Order Interaction, and Stabilized Semantic Inference

arXiv:2607.20451v1 Announce Type: new Abstract: Semantic Field Theory (SFT) has developed from a philosophical critique of strong anti-formalist readings of language games into a proposed computationa

Semantics at an Angle: When Cosine Similarity Works Until It Doesn't

arXiv:2504.16318v3 Announce Type: replace Abstract: Cosine similarity is a standard comparison rule for learned representations in information retrieval, natural language processing, computer vision,

ShriNep@EEUCA 2026: RAKSHAK - Multi-Task DeBERTa with Rationale Distillation and Jigsaw-Augmented Training for Toxic Intent Classification

arXiv:2607.20450v1 Announce Type: new Abstract: This paper presents two systems for the GameTox Shared Task at the Workshop on EEUCA at ACL 2026, which requires classifying World of Tanks chat utteran

SiGMA: Sign-Guided Merging and Adaptation for Multimodal Continual Instruction Tuning

arXiv:2607.20511v1 Announce Type: new Abstract: Multimodal Continual Instruction Tuning (MCIT) is crucial for adapting Multimodal Large Language Models (MLLMs) to evolving a sequence of downstream tas

Socially Consistent Multi-Robot Navigation Using Decoupled Planning and Trajectory Coordination

arXiv:2607.20772v1 Announce Type: new Abstract: The successful integration of mobile robots in human-centric environments requires navigation that is not only safe and efficient, but also predictable

researcharxiv-cs-ro

Sparse Concept Channels in Frozen 3D CT Vision Encoders

arXiv:2607.20993v1 Announce Type: cross Abstract: Large vision-language models are becoming increasingly dominant in 3D medical image interpretation, but we rarely know which internal units encode cli

SPDCN: Strip-based Deformable Convolutional Network for Steel Surface Defect Segmentation

arXiv:2607.21456v1 Announce Type: new Abstract: Steel surface defect segmentation is critical for industrial quality inspection, yet existing methods struggle with elongated, anisotropic defects such

Spectral Concentration and Recovery in Sparse High-Dimensional Random Geometric Graphs

arXiv:2607.14304v2 Announce Type: replace-cross Abstract: We study sparse threshold random geometric graphs generated by high-dimensional spherical or Gaussian latent vectors. Although each edge has m

Stochastic Sampling is Epistemically Shallow: The Dimensionality Gap Between Temperature Variation and Model Diversity in LLMs

arXiv:2607.20464v1 Announce Type: new Abstract: When a language model gives different answers on repeated runs, does that variation reveal what it does not know? Self-consistency turns the variation i

StrideDiffusion: Accelerating Diffusion Models for Time-series Generation

arXiv:2607.20545v1 Announce Type: new Abstract: Diffusion models have become competitive generators for time series, but their practical use is limited by the large number of sequential denoising step

Structure-Preserving Physics-Informed Neural Network for the Korteweg--de Vries (KdV) Equation

arXiv:2511.00418v2 Announce Type: replace Abstract: Physics-Informed Neural Networks (PINNs) offer a flexible framework for solving nonlinear partial differential equations (PDEs), yet conventional im

SubSplat: High-Resolution Pixel-aligned 3DGS via Sub-pixel Gaussian Reparameterization

arXiv:2607.20813v1 Announce Type: new Abstract: Pixel-aligned Gaussian splatting enables efficient and generalizable novel-view synthesis. However, high-resolution rendering faces a critical trade-off

Surprisal Theory is Tautological (without Rational Grounding)

arXiv:2607.21574v1 Announce Type: new Abstract: Surprisal theory holds that the human processing difficulty of a linguistic unit in context is an affine function of its surprisal under some language m

TabPFN beyond Tabular Data: Calibration and Accuracy on Multimodal Embeddings

arXiv:2607.11007v2 Announce Type: replace Abstract: Few-shot multimodal classification commonly attaches a lightweight head, such as k-nearest neighbors, logistic regression, or a linear SVM, to a fro

Tackling Heterogeneity in Federated Learning via Variance-Reduced Boltzmann Sampling within Homogeneous Social Coalitions

arXiv:2506.02897v3 Announce Type: replace Abstract: Federated Learning (FL) enables privacy-preserving collaborative model training, but its effectiveness is often limited by client data heterogeneity

Texture++: Elevating 3D Asset Texture Resolution with a Region-Aware Diffusion Model

arXiv:2607.21504v1 Announce Type: new Abstract: Numerous 3D assets are discarded due to low texture resolution, while current super-resolution models ignore texture maps and focus on natural images. A

The Active Ingredient in Muon's Grokking

arXiv:2607.20512v1 Announce Type: cross Abstract: The Muon optimizer reaches the grokking threshold on modular arithmetic faster than AdamW. Prior work attributes this to 'spectral-norm constraints pl

The Human-AI Substitution Principle: When will you be replaced by AI in your organization?

arXiv:2607.20781v1 Announce Type: new Abstract: Artificial Intelligence (AI) is rapidly transforming organizations, raising a fundamental organizational and economic question: when will a human employ

The Price of Hidden Curvature: An widetilde{Omega} (d^{5/4} sqrt{T}) Lower Bound for Bandit Convex Optimization

arXiv:2607.18652v2 Announce Type: replace-cross Abstract: We establish a widetildeOmega(d^{5/4}sqrt T) lower bound on the minimax expected regret of stochastic bandit convex optimization of 1-Lipschit

The Weight of Silence: A Causal Case for Weights Over the Scratchpad in Latent Chess Reasoning

arXiv:2607.20952v1 Announce Type: cross Abstract: Latent, or silent, reasoning lets language models carry out intermediate computation in continuous vector space instead of words, and is widely assume

Thermodynamic Weight Decay: Exploring Grokking Acceleration via Attention Specific Heat

arXiv:2607.20552v1 Announce Type: new Abstract: Grokking -- the delayed generalization of neural networks long after they have memorized their training data -- wastes thousands of training epochs and

Thinkink: 2D Spatial Ink-native Interaction with LLMs

arXiv:2607.21468v1 Announce Type: cross Abstract: People often use handwritten notes and sketches to externalize ideas for ideation. To integrate large language models (LLMs) into this practice, we pr

THOR: A Theta-Gamma Hierarchical Oscillatory Reasoning Framework for Multi-hop QA

arXiv:2607.20459v1 Announce Type: cross Abstract: Multi-hop question answering requires retrieving and integrating evidence from multiple contexts. Despite the rapid progress of current research, mult

Through-the-Earth Magnetic Induction Communication and Networking: A Comprehensive Survey

arXiv:2510.14854v4 Announce Type: cross Abstract: Magnetic induction (MI) communication (MIC) has emerged as a promising candidate for underground communication networks due to its excellent penetrati

Towards a Certifying Grounder

arXiv:2607.21199v1 Announce Type: cross Abstract: Grounding, the translation of high-level theories into equivalent quantifier-free formulas, is a crucial step in declarative solving, yet it has so fa

Towards Capability-Aware Traversability Navigation for Unstructured Environments

arXiv:2607.20679v1 Announce Type: new Abstract: Estimating traversability in unstructured environments requires conditioning on robot embodiment, as the same terrain can be traversable for one platfor

researcharxiv-cs-ro

Towards Robust Iris Recognition Through Occlusion Identification and Conditional Diffusion-Based Reconstruction

arXiv:2607.21545v1 Announce Type: new Abstract: Iris recognition is a reliable biometric approach that identifies individuals using the distinctive and stable texture of the iris. However, recognition

Tractable Hierarchical Control of Autoregressive Language Models

arXiv:2607.20483v1 Announce Type: new Abstract: Constraining the generation of autoregressive large language models (LLMs) is an important component of integrating language models into formal systems.

Transformer-Assisted LLM-Based Source Code Summarisation: to Enable More Secure Software Development

arXiv:2607.20933v1 Announce Type: cross Abstract: Neural Source Code Summarisation (NSCS) aims to generate natural language summaries of source code to improve developers' and maintainers' understandi

Transformer-based Diffusion models for Hydrological Time Series Probabilistic Imputation and Forecasting

arXiv:2607.21200v1 Announce Type: cross Abstract: The modeling of hydrometeorological time series with limited observations is a key challenge in the monitoring of hydro-systems and water resources, a

Transition-Related Potentials as Markers of Narrative Comprehension in Continuous EEG

arXiv:2607.20720v1 Announce Type: cross Abstract: Harnessing the potential of electroencephalography (EEG) for brain research is fundamentally limited by intrinsic noise and the diffuse projection of