research

Decomposing the Depth Profile of Fine-Tuning

arXiv:2604.17177v1 Announce Type: new Abstract: Fine-tuning adapts pretrained networks to new objectives. Whether the resulting depth profile of representational change reflects an intrinsic property

DeepDetect: Learning All-in-One Dense Keypoints

arXiv:2510.17422v4 Announce Type: replace Abstract: Keypoint detection is the foundation of many computer vision tasks, including image registration, structure-from-motion, 3D reconstruction, visual o

researcharxiv-cs-cv

21 Apr 2026

DeepRitzSplit Neural Operator for Phase-Field Models via Energy Splitting

arXiv:2604.18261v1 Announce Type: cross Abstract: The multi-scale and non-linear nature of phase-field models of solidification requires fine spatial and temporal discretization, leading to long compu

Defragmenting Language Models: An Interpretability-based Approach for Vocabulary Expansion

arXiv:2604.16656v1 Announce Type: new Abstract: All languages are equal; when it comes to tokenization, some are more equal than others. Tokens are the hidden currency that dictate the cost and latenc

DeInfer: Efficient Parallel Inferencing for Decomposed Large Language Models

arXiv:2604.17709v1 Announce Type: new Abstract: Existing works on large language model (LLM) decomposition mainly focus on improving performance on downstream tasks, but they ignore the poor parallel

Demonstrating Real Advantage of Machine-Learning-Enhanced Monte Carlo for Combinatorial Optimization

arXiv:2510.19544v2 Announce Type: replace-cross Abstract: Combinatorial optimization problems are central to both practical applications and the development of optimization methods. While classical an

Depth Adaptive Efficient Visual Autoregressive Modeling

arXiv:2604.17286v1 Announce Type: new Abstract: Visual Autoregressive (VAR) modeling inefficiently applies a fixed computational depth to each position when generating high-resolution images. While ex

DGSSM: Diffusion guided state-space models for multimodal salient object detection

arXiv:2604.17585v1 Announce Type: new Abstract: Salient object detection (SOD) requires modeling both long-range contextual dependencies and fine-grained structural details, which remains challenging

DiffuSAM: Diffusion Guided Zero-Shot Object Grounding for Remote Sensing Imagery

arXiv:2604.18201v1 Announce Type: new Abstract: Diffusion models have emerged as powerful tools for a wide range of vision tasks, including text-guided image generation and editing. In this work, we e

Diffusion-Based Optimization for Accelerated Convergence of Redundant Dual-Arm Minimum Time Problems

arXiv:2604.16670v1 Announce Type: new Abstract: We present a framework leveraging a novel variant of the model-based diffusion algorithm to minimize the time required for a redundant dual-arm robot co

researcharxiv-cs-ro

Digging for clues about the North Pole’s past

In the past, even with an icebreaker and during peak melt season, getting to the North Pole wasn’t a sure bet. It took favorable winds to crack the frozen ocean surface, and ships had to fight through

researchmit-tech-review

Dimensional Criticality at Grokking Across MLPs and Transformers

arXiv:2604.16431v1 Announce Type: new Abstract: Abrupt transitions between distinct dynamical regimes are a hallmark of complex systems. Grokking in deep neural networks provides a striking example --

DisCa: Accelerating Video Diffusion Transformers with Distillation-Compatible Learnable Feature Caching

arXiv:2602.05449v3 Announce Type: replace Abstract: While diffusion models have achieved great success in the field of video generation, this progress is accompanied by a rapidly escalating computatio

Distributionally Robust Regret Optimal Control Under Moment-Based Ambiguity Sets

arXiv:2512.10906v2 Announce Type: replace-cross Abstract: We consider a class of finite-horizon, linear-quadratic stochastic control problems, where the probability distribution governing the noise pr

Do LLMs Encode Functional Importance of Reasoning Tokens?

arXiv:2601.03066v2 Announce Type: replace Abstract: Large language models solve complex tasks by generating long reasoning chains, achieving higher accuracy at the cost of increased computational cost

Does AI See like Art Historians? Interpreting How Vision Language Models Recognize Artistic Style

arXiv:2603.11024v2 Announce Type: replace Abstract: VLMs have become increasingly proficient at a range of computer vision tasks, such as visual question answering and object detection. This includes

Domain-Specialized Object Detection via Model-Level Mixtures of Experts

arXiv:2604.18256v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models provide a structured approach to combining specialized neural networks and offer greater interpretability than conventio

DSA-CycleGAN: A Domain Shift Aware CycleGAN for Robust Multi-Stain Glomeruli Segmentation

arXiv:2604.18368v1 Announce Type: new Abstract: A key challenge in segmentation in digital histopathology is inter- and intra-stain variations as it reduces model performance. Labelling each stain is

Dual-End Consistency Model

arXiv:2602.10764v2 Announce Type: replace Abstract: The slow iterative sampling nature remains a major bottleneck for the practical deployment of diffusion and flow-based generative models. While cons

Dual Strategies for Test-Time Adaptation

arXiv:2604.17542v1 Announce Type: new Abstract: Conventional test-time adaptation (TTA) approaches typically adapt the model using only a small fraction of test samples, often those with low-entropy p

Duality for the Adversarial Total Variation

arXiv:2604.18540v1 Announce Type: cross Abstract: Adversarial training of binary classifiers can be reformulated as regularized risk minimization involving a nonlocal total variation. Building on this

DualToken: Towards Unifying Visual Understanding and Generation with Dual Visual Vocabularies

arXiv:2503.14324v3 Announce Type: replace-cross Abstract: The differing representation spaces required for visual understanding and generation pose a challenge in unifying them within the autoregressi

Dynamic Eraser for Guided Concept Erasure in Diffusion Models

arXiv:2604.16483v1 Announce Type: new Abstract: Concept erasure in Text-To-Image (T2I) diffusion models is vital for safe content generation, but existing inference-time methods face significant limit

Dynamic Risk Assessment by Bayesian Attack Graphs and Process Mining

arXiv:2604.18080v1 Announce Type: cross Abstract: While attack graphs are useful for identifying major cybersecurity threats affecting a system, they do not provide operational support for determining

E2E-GMNER: End-to-End Generative Grounded Multimodal Named Entity Recognition

arXiv:2604.17319v1 Announce Type: cross Abstract: Grounded Multimodal Named Entity Recognition (GMNER) aims to jointly identify named entity mentions in text, predict their semantic types, and ground

E2E-WAVE: End-to-End Learned Waveform Generation for Underwater Video Multicasting

arXiv:2604.17047v1 Announce Type: cross Abstract: We present E2E-WAVE, the first end-to-end learned waveform generation system for underwater video multicasting. Acoustic channels exhibit 20--46% bit

EarthSight: A Distributed Framework for Low-Latency Satellite Intelligence

arXiv:2511.10834v3 Announce Type: replace Abstract: Low-latency delivery of satellite imagery is essential for time-critical applications such as disaster response, intelligence, and infrastructure mo

EAST: Early Action Prediction Sampling Strategy with Token Masking

arXiv:2604.18367v1 Announce Type: new Abstract: Early action prediction seeks to anticipate an action before it fully unfolds, but limited visual evidence makes this task especially challenging. We in

eCP: Equivariant Conformal Prediction with pre-trained models

arXiv:2602.03986v2 Announce Type: replace Abstract: Conformal prediction, a post-hoc, distribution-free, finite-sample method of uncertainty quantification that offers formal coverage guarantees under

EdgeVTP: Exploration of Latency-efficient Trajectory Prediction for Edge-based Embedded Vision Applications

arXiv:2604.16783v1 Announce Type: new Abstract: Vehicle trajectory prediction is central to highway perception, but deployment on roadside edge devices necessitates bounded, deterministic end-to-end l

EEG-Based Emergency Braking Intensity Prediction Using Blind Source Separation

arXiv:2604.18220v1 Announce Type: cross Abstract: Electroencephalography (EEG) signals have been promising for long-term braking intensity prediction but are prone to various artifacts that limit thei

Efficient Inference for Coupled Hidden Markov Models in Continuous Time and Discrete Space

arXiv:2510.12916v2 Announce Type: replace-cross Abstract: Systems of interacting continuous-time Markov chains are a powerful model class, but inference is typically intractable in high dimensional se

Efficient Low-Resource Language Adaptation via Multi-Source Dynamic Logit Fusion

arXiv:2604.18106v1 Announce Type: new Abstract: Adapting large language models (LLMs) to low-resource languages (LRLs) is constrained by the scarcity of task data and computational resources. Although

Ego-InBetween: Generating Object State Transitions in Ego-Centric Videos

arXiv:2604.17749v1 Announce Type: new Abstract: Understanding physical transformation processes is crucial for both human cognition and artificial intelligence systems, particularly from an egocentric

Eluder dimension: localise it!

arXiv:2601.09825v2 Announce Type: replace Abstract: We establish a lower bound on the eluder dimension of generalised linear model classes, showing that standard eluder dimension-based analysis cannot

EmbodiedHead: Real-Time Listening and Speaking Avatar for Conversational Agents

arXiv:2604.17211v1 Announce Type: new Abstract: We present EmbodiedHead, a speech-driven talking-head framework that equips LLMs with real-time visual avatars for conversation. A practical embodied av

Emergent Structured Representations Support Flexible In-Context Inference in Large Language Models

arXiv:2602.07794v3 Announce Type: replace Abstract: Large language models (LLMs) exhibit emergent behaviors suggestive of human-like reasoning. While recent work has identified structured conceptual r

emg2speech: Synthesizing speech from electromyography using self-supervised speech models

arXiv:2510.23969v2 Announce Type: replace-cross Abstract: We present a neuromuscular speech interface that translates electromyographic (EMG) signals recorded from orofacial muscles during speech arti

Emotion Collider: Dual Hyperbolic Mirror Manifolds for Sentiment Recovery via Anti Emotion Reflection

arXiv:2602.16161v3 Announce Type: replace-cross Abstract: Emotional expression underpins natural communication and effective human-computer interaction. We present Emotion Collider (EC-Net), a hyperbo

EmoVerse: A MLLMs-Driven Emotion Representation Dataset for Interpretable Visual Emotion Analysis

arXiv:2511.12554v2 Announce Type: replace Abstract: Visual Emotion Analysis (VEA) aims to bridge the affective gap between visual content and human emotional responses. Despite its promise, progress i

En 2021, les opposants à la vaccination craignaient 'une hécatombe' dans les années à venir. Nous sommes 5 ans plus tard et une immense étud…

En 2021, les opposants à la vaccination craignaient 'une hécatombe' dans les années à venir. Nous sommes 5 ans plus tard et une immense étude sur les données de 29 millions de Français (23 millions va

researchyann-lecun--x

Enabling Stroke-Level Structural Analysis of Hieroglyphic Scripts without Language-Specific Priors

arXiv:2601.05508v2 Announce Type: replace-cross Abstract: Hieroglyphs, as logographic writing systems, encode rich semantic and cultural information within their internal structural composition. Yet,

Enhancing Anomaly-Based Intrusion Detection Systems with Process Mining

arXiv:2604.18066v1 Announce Type: cross Abstract: Anomaly-based Intrusion Detection Systems (IDSs) ensure protection against malicious attacks on networked systems. While deep learning-based IDSs achi

Enhancing classification accuracy through chaos

arXiv:2603.15299v2 Announce Type: replace Abstract: We propose a novel approach which exploits chaos to enhance classification accuracy. Specifically, the available data that need to be classified are

Enhancing Trust in Large Language Models via Uncertainty-Calibrated Fine-Tuning

arXiv:2412.02904v2 Announce Type: replace Abstract: Large language models (LLMs) have revolutionized the field of natural language processing with their impressive reasoning and question-answering cap

Enhancing Zero-shot Personalized Image Aesthetics Assessment with Profile-aware Multimodal LLM

arXiv:2604.17233v1 Announce Type: new Abstract: Personalized image aesthetics assessment (PIAA) aims to predict an individual user's subjective rating of an image, which requires modeling user-specifi

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs

arXiv:2510.00861v2 Announce Type: replace Abstract: While search-augmented large language models (LLMs) exhibit impressive capabilities, their reliability in complex multi-hop reasoning remains limite

Establishing a Scale for Kullback-Leibler Divergence in Language Models Across Various Settings

arXiv:2505.15353v3 Announce Type: replace Abstract: Log-likelihood vectors define a common space for comparing language models as probability distributions, enabling unified comparisons across heterog