research

BoxTuning: Directly Injecting the Object Box for Multimodal Model Fine-Tuning

arXiv:2604.11136v1 Announce Type: cross Abstract: Object-level spatial-temporal understanding is essential for video question answering, yet existing multimodal large language models (MLLMs) encode fr

Research

Breaking the KV Cache Bottleneck: Fan Duality Model Achieves O(1) Decode Memory with Superior Associative Recall

DGX agent

arXiv:2604.07716v2 Announce Type: replace Abstract: We present FDM (Fan Duality Model), a linear sequence architecture that resolves the fundamental tension between memory efficiency and associative r

researcharxiv-cs-lg

14 Apr 2026

Brief2Design: A Multi-phased, Compositional Approach to Prompt-based Graphic Design

arXiv:2604.11019v1 Announce Type: cross Abstract: Professional designers work from client briefs that specify goals and constraints but often lack concrete design details. Translating these abstract r

Bringing Value Models Back: Generative Critics for Value Modeling in LLM Reinforcement Learning

arXiv:2604.10701v1 Announce Type: cross Abstract: Credit assignment is a central challenge in reinforcement learning (RL). Classical actor-critic methods address this challenge through fine-grained ad

Byte-level generative predictions for forensics multimedia carving

arXiv:2604.11010v1 Announce Type: new Abstract: Digital forensic investigations often face significant challenges when recovering fragmented multimedia files that lack file system metadata. While trad

Byzantine-Robust Distributed SGD: A Unified Analysis and Tight Error Bounds

arXiv:2604.10179v1 Announce Type: cross Abstract: Byzantine-robust distributed optimization relies on robust aggregation rules to mitigate the influence of malicious Byzantine workers. Despite the pro

CableTract: A Co-Designed Cable-Driven Field Robot for Low-Compaction, Off-Grid Capable Agriculture

arXiv:2604.09938v1 Announce Type: cross Abstract: Conventional field operations spend most of their energy moving the tractor body, not the implement. Yet feasibility studies for novel agricultural ve

CAGE: Bridging the Accuracy-Aesthetics Gap in Educational Diagrams via Code-Anchored Generative Enhancement

arXiv:2604.09691v1 Announce Type: cross Abstract: Educational diagrams -- labeled illustrations of biological processes, chemical structures, physical systems, and mathematical concepts -- are essenti

CapBench: A Multi-PDK Dataset for Machine-Learning-Based Post-Layout Capacitance Extraction

arXiv:2604.11202v1 Announce Type: cross Abstract: We present CapBench, a fully reproducible, multi-PDK dataset for capacitance extraction. The dataset is derived from open-source designs, including si

Catalog-Native LLM: Speaking Item-ID Dialect with Less Entanglement for Recommendation

arXiv:2510.05125v2 Announce Type: replace Abstract: While collaborative filtering delivers predictive accuracy and efficiency, and Large Language Models (LLMs) enable expressive and generalizable reas

researcharxiv-cs-cl

Catalyst: Out-of-Distribution Detection via Elastic Scaling

arXiv:2602.02409v2 Announce Type: replace Abstract: Out-of-distribution (OOD) detection is critical for the safe deployment of deep neural networks. State-of-the-art post-hoc methods typically derive

CausalGaze: Unveiling Hallucinations via Counterfactual Graph Intervention in Large Language Models

arXiv:2604.11087v1 Announce Type: new Abstract: Despite the groundbreaking advancements made by large language models (LLMs), hallucination remains a critical bottleneck for their deployment in high-s

Choose Your Battles: Distributed Learning Over Multiple Tug of War Games

arXiv:2509.20147v2 Announce Type: replace-cross Abstract: Consider N players and K games taking place simultaneously. Each of these games is modeled as a Tug-of-War (ToW) game where increasing the act

CircuitSynth: Reliable Synthetic Data Generation

arXiv:2604.10114v1 Announce Type: cross Abstract: The generation of high-fidelity synthetic data is a cornerstone of modern machine learning, yet Large Language Models (LLMs) frequently suffer from ha

City-Wide Low-Altitude Urban Air Mobility: A Scalable Global Path Planning Approach via Risk-Aware Multi-Scale Cell Decomposition

arXiv:2408.02786v4 Announce Type: replace Abstract: The realization of Urban Air Mobility (UAM) necessitates scalable global path planning algorithms capable of ensuring safe navigation within complex

researcharxiv-cs-ro

CLAW: Composable Language-Annotated Whole-body Motion Generation

arXiv:2604.11251v1 Announce Type: new Abstract: Training language-conditioned whole-body controllers for humanoid robots requires large-scale datasets pairing motion trajectories with natural-language

researcharxiv-cs-ro

ClawBench: Can AI Agents Complete Everyday Online Tasks? 153 tasks, 144 live websites, best model at 33.3% [R]

researchr-machinelearning

ClawBench is a benchmark of 153 everyday web tasks spanning 144 live platforms across 15 categories — from completing purchases and booking appointments to submitting job applications. Unlike existing

CLAY: Conditional Visual Similarity Modulation in Vision-Language Embedding Space

arXiv:2604.11539v1 Announce Type: cross Abstract: Human perception of visual similarity is inherently adaptive and subjective, depending on the users' interests and focus. However, most image retrieva

CodaRAG: Connecting the Dots with Associativity Inspired by Complementary Learning

arXiv:2604.10426v1 Announce Type: cross Abstract: Large Language Models (LLMs) struggle with knowledge-intensive tasks due to hallucinations and fragmented reasoning over dispersed information. While

Cognitive Training for Language Models: Towards General Capabilities via Cross-Entropy Games

arXiv:2603.22479v3 Announce Type: replace-cross Abstract: Defining a constructive process to build general capabilities for language models in an automatic manner is considered an open problem in arti

CoMelSinger: Discrete Token-Based Zero-Shot Singing Synthesis With Structured Melody Control and Guidance

arXiv:2509.19883v2 Announce Type: replace-cross Abstract: Singing Voice Synthesis (SVS) aims to generate expressive vocal performances from structured musical inputs such as lyrics and pitch sequences

Coming soon: 10 Things That Matter in AI Right Now

Each year we compile our 10 Breakthrough Technologies list, featuring our educated predictions for which technologies will have the biggest impact on how we live and work. This year, however, we had a

researchmit-tech-review

Communication-Efficient Gluon in Federated Learning

arXiv:2604.10689v1 Announce Type: new Abstract: Recent developments have shown that Muon-type optimizers based on linear minimization oracles (LMOs) over non-Euclidean norm balls have the potential to

Compact single-shot ranging and near-far imaging using metasurfaces

arXiv:2604.10037v1 Announce Type: cross Abstract: We present a metasurface imaging system capable of simultaneously capturing two images at close range (1-2~cm) and an additional image at long range (

Computation of Least Trimmed Squares: A Branch-and-Bound framework with Hyperplane Arrangement Enhancements

arXiv:2604.11584v1 Announce Type: cross Abstract: We study computational aspects of a key problem in robust statistics -- the penalized least trimmed squares (LTS) regression problem, a robust estimat

Computational Implementation of a Model of Category-Theoretic Metaphor Comprehension

arXiv:2604.10035v1 Announce Type: cross Abstract: In this study, we developed a computational implementation for a model of metaphor comprehension based on the theory of indeterminate natural transfor

ConceptPose: Training-Free Zero-Shot Object Pose Estimation using Concept Vectors

arXiv:2512.09056v3 Announce Type: replace Abstract: Object pose estimation is a fundamental task in computer vision and robotics, yet most methods require extensive, dataset-specific training. Concurr

Constrained Assumption-Based Argumentation Frameworks

arXiv:2602.13135v2 Announce Type: replace Abstract: Assumption-based Argumentation (ABA) is a well-established form of structured argumentation. ABA frameworks with an underlying atomic language are w

Continuous PT-Symmetry Breaking as a Design Variable for Giant Altermagnetic Spin Splitting

arXiv:2604.10173v1 Announce Type: cross Abstract: Magnetic point-group analysis classifies altermagnets but returns only a binary symmetry verdict, leaving spin-splitting energy (SSE) inaccessible wit

Continuous-time Online Learning via Mean-Field Neural Networks: Regret Analysis in Diffusion Environments

arXiv:2604.10958v1 Announce Type: cross Abstract: We study continuous-time online learning where data are generated by a diffusion process with unknown coefficients. The learner employs a two-layer ne

ConvFormer3D-TAP: Phase/Uncertainty-Aware Front-End Fusion for Cine CMR View Classification Pipelines

arXiv:2604.11389v1 Announce Type: new Abstract: Reliable recognition of standard cine cardiac MRI views is essential because each view determines which cardiac anatomy is visualized and which quantita

COREY: A Prototype Study of Entropy-Guided Operator Fusion with Hadamard Reparameterization for Selective State Space Models

arXiv:2604.10597v1 Announce Type: cross Abstract: State Space Models (SSMs), represented by the Mamba family, provide linear-time sequence modeling and are attractive for long-context inference. Yet p

Critical-CoT: A Robust Defense Framework against Reasoning-Level Backdoor Attacks in Large Language Models

arXiv:2604.10681v1 Announce Type: cross Abstract: Large Language Models (LLMs), despite their impressive capabilities across domains, have been shown to be vulnerable to backdoor attacks. Prior backdo

CUTEv2: Unified and Configurable Matrix Extension for Diverse CPU Architectures with Minimal Design Overhead

arXiv:2604.11615v1 Announce Type: cross Abstract: Matrix extensions have emerged as an essential feature in modern CPUs to address the surging demands of AI workloads. However, existing designs often

CWCD: Category-Wise Contrastive Decoding for Structured Medical Report Generation

arXiv:2604.10410v1 Announce Type: new Abstract: Interpreting chest X-rays is inherently challenging due to the overlap between anatomical structures and the subtle presentation of many clinically sign

CylinderDepth: Cylindrical Spatial Attention for Multi-View Consistent Self-Supervised Surround Depth Estimation

arXiv:2511.16428v3 Announce Type: replace Abstract: Self-supervised surround-view depth estimation enables dense, low-cost 3D perception with a 360{eg} field of view from multiple minimally overlappin

DA-PTQ: Drift-Aware Post-Training Quantization for Efficient Vision-Language-Action Models

arXiv:2604.11572v1 Announce Type: new Abstract: Vision-Language-Action models (VLAs) have demonstrated strong potential for embodied AI, yet their deployment on resource-limited robots remains challen

researcharxiv-cs-ro

Daily Predictions of F10.7 and F30 Solar Indices with Deep Learning

arXiv:2604.10045v1 Announce Type: cross Abstract: The F10.7 and F30 solar indices are the solar radio fluxes measured at wavelengths of 10.7 cm and 30 cm, respectively, which are key indicators of sol

Dark-EvGS: Event Camera as an Eye for Radiance Field in the Dark

arXiv:2507.11931v2 Announce Type: replace Abstract: In low-light environments, conventional cameras often struggle to capture clear multi-view images of objects due to dynamic range limitations and mo

Data-Efficient Surgical Phase Segmentation in Small-Incision Cataract Surgery: A Controlled Study of Vision Foundation Models

arXiv:2604.10514v1 Announce Type: cross Abstract: Surgical phase segmentation is central to computer-assisted surgery, yet robust models remain difficult to develop when labeled surgical videos are sc

Decoding Ancient Oracle Bone Script via Generative Dictionary Retrieval

arXiv:2604.09668v1 Announce Type: cross Abstract: Understanding humanity's earliest writing systems is crucial for reconstructing civilization's origins, yet many ancient scripts remain undeciphered.

Decoupled Generative Modeling for Human-Object Interaction Synthesis

arXiv:2512.19049v2 Announce Type: replace Abstract: Synthesizing realistic human-object interaction (HOI) is essential for 3D computer vision and robotics, underpinning animation and embodied control.

Decoupled Similarity for Task-Aware Token Pruning in Large Vision-Language Models

arXiv:2604.11240v1 Announce Type: new Abstract: Token pruning has emerged as an effective approach to reduce the substantial computational overhead of Large Vision-Language Models (LVLMs) by discardin

DeCoVec: Building Decoding Space based Task Vector for Large Language Models via In-Context Learning

arXiv:2604.11129v1 Announce Type: new Abstract: Task vectors, representing directions in model or activation spaces that encode task-specific behaviors, have emerged as a promising tool for steering l

researcharxiv-cs-cl

DeepShapeMatchingKit: Accelerated Functional Map Solver and Shape Matching Pipelines Revisited

arXiv:2604.10377v1 Announce Type: new Abstract: Deep functional maps, leveraging learned feature extractors and spectral correspondence solvers, are fundamental to non-rigid 3D shape matching. Based o

DeepSketcher: Internalizing Visual Manipulation for Multimodal Reasoning

arXiv:2509.25866v2 Announce Type: replace Abstract: The 'thinking with images' paradigm represents a pivotal shift in the reasoning of Vision Language Models (VLMs), moving from text-dominant chain-of

Defending against Backdoor Attacks via Module Switching

arXiv:2504.05902v2 Announce Type: replace-cross Abstract: Backdoor attacks pose a serious threat to deep neural networks (DNNs), allowing adversaries to implant triggers for hidden behaviors in infere

researcharxiv-cs-cl

Delving Aleatoric Uncertainty in Medical Image Segmentation via Vision Foundation Models

arXiv:2604.10963v1 Announce Type: new Abstract: Medical image segmentation supports clinical workflows by precisely delineating anatomical structures and lesions. However, medical image datasets medic