Search: “research”

Memory-Based vs. Context-Only Conditioning Produces Distinct Behavioral Patterns in Stateful Personalization

arXiv:2605.27389v1 Announce Type: cross Abstract: We study how conditioning context shapes personalization behavior in a teacher-facing educational recommender system. We compare contextual conditioni

Research

MERIT: Matching Expertise via Rubric-Informed Training for Reviewer Assignment

DGX agent

arXiv:2605.27865v1 Announce Type: new Abstract: Matching submissions with suitable reviewers at scale is a growing challenge for major venues, yet existing approaches either rely on coarse proxy signa

researcharxiv-cs-cl

28 May 2026

Metric-Aware PCA as a Linear Instance of Geometric Deep Learning

arXiv:2605.27456v1 Announce Type: new Abstract: Geometric deep learning organises neural architectures around the symmetries of their data domain, with the choice of symmetry group serving as a geomet

MGRetrieval: Memory-Guided Reflective Retrieval for Long-Term Dialogue Agents

arXiv:2605.27437v1 Announce Type: cross Abstract: Large Language Models (LLMs) have made significant progress in dialogue, yet redundant memory contexts severely limit their effectiveness in long-term

Mind the Gap: Mixtures of Gaussians in Approximate Differential Privacy

arXiv:2605.28078v1 Announce Type: cross Abstract: We design a class of additive noise mechanisms that satisfy ((arepsilon, elta))-differential privacy (DP) for scalar, real-valued query functions with

MORI-Seg: Learning Morphological Geometry for Instance Segmentation without Instance Annotations

arXiv:2605.28261v1 Announce Type: new Abstract: Instance-level quantification of kidney functional units is essential for morphometric analysis, yet most publicly available pathology datasets provide

Multi-Mixer Models: Flexible Sequence Modeling with Shared Representations

arXiv:2605.28769v1 Announce Type: new Abstract: Softmax attention is the cornerstone of modern large language models, but its memory scales linearly and compute quadratically with sequence length. Lin

Natural Functional Gradients for Smooth Trajectory Optimization

arXiv:2605.28202v1 Announce Type: new Abstract: Generating collision-free and smooth motions remains a central challenge in robotic manipulation, particularly in cluttered environments and narrow pass

Natural Locomotion: Principle and Method

arXiv:2605.28254v1 Announce Type: new Abstract: Robotic locomotion can become efficient when mechanisms exploit passive dynamics, compliance, and resonance rather than track prescribed trajectories. T

Neural Quantum Spectral Operator Learning for Solving Partial Differential Equations

arXiv:2605.27408v1 Announce Type: cross Abstract: Partial differential equations (PDEs) are central to modeling physical and engineering systems, but repeatedly solving parametric PDEs remains computa

Neural Weight Compression for Language Models

arXiv:2510.11234v3 Announce Type: replace Abstract: Efficient compression of language model weights is increasingly critical as model scale and deployment grow. Yet, most existing methods rely on hand

Industry

📢 New @heyjasper release ! 📢 MONET 🌸 : An Apache2.0 deduped and recaptioned dataset of 105M samples unlocking reproducible text-to-image …

📢 New @heyjasper release ! 📢 MONET 🌸 : An Apache2.0 deduped and recaptioned dataset of 105M samples unlocking reproducible text-to-image research. Nano T2I 🖌️ : A codebase to train your own T2I model

industryclem-delangue--x

Next-Scale Autoregressive Models for Text-to-Motion Generation

arXiv:2604.03799v2 Announce Type: replace Abstract: Autoregressive (AR) models offer stable and efficient training, but standard next-token prediction is not well aligned with the temporal structure r

Noise Scheduling as Information-Guided Allocation in Diffusion Training

arXiv:2602.18647v2 Announce Type: replace-cross Abstract: We introduce InfoNoise, an online adaptive noise schedule for diffusion training that reallocates optimization effort toward noise levels wher

Not All NVFP4 QAT Recipes Are Equal: How Architecture and Scale Shape Model Quality for Anomaly Segmentation

arXiv:2605.27616v1 Announce Type: cross Abstract: Real-time anomaly segmentation demands both high recall and efficient low-precision inference. We study the three-way interaction of model architectur

NUCLEUS-MoE: Unified Model of Pool Boiling for Liquid Cooling

arXiv:2605.27722v1 Announce Type: new Abstract: Two-phase boiling enables heat transfer rates an order of magnitude higher than single-phase cooling, but it remains difficult to model due to the stron

Object-Centric Vision Token Pruning for Vision Language Models

arXiv:2511.20439v2 Announce Type: replace-cross Abstract: In Vision Language Models (VLMs), vision tokens are quantity-heavy yet information-dispersed compared with language tokens, thus consume too m

Ocean4Rec: Offline LLM-Derived OCEAN Profiles for Request-Time VOD Reranking

arXiv:2605.27429v1 Announce Type: cross Abstract: Industrial video-on-demand (VOD) recommenders need richer content understanding, but LLM-as-reranker designs repeat prompt construction, token generat

OmniEgo-R^2: A Routed Reasoning Framework for the 1st Cross-Domain EgoCross Challenge at CVPR 2026

arXiv:2605.24481v2 Announce Type: replace Abstract: The 1st Cross-Domain EgoCross Challenge at EgoVis, CVPR 2026 evaluates whether multimodal large language models can reason over egocentric videos ac

On the Fallacy of Global Token Perplexity in Spoken Language Model Evaluation

arXiv:2601.06329v2 Announce Type: replace-cross Abstract: Generative spoken language models pretrained on large-scale raw audio can continue a speech prompt with appropriate content while preserving a

On the Learnability of Test-Time Adaptation: A Recovery Complexity Perspective

arXiv:2605.28057v1 Announce Type: cross Abstract: Test-time adaptation (TTA) aims to adapt models to maintain reliable performance on non-stationary test streams without requiring labeled data. Despit

On the Origin of Synthetic Information by Means of Steganographic Inheritance

arXiv:2605.27551v1 Announce Type: new Abstract: The origin of species has been the mystery of mysteries in natural science. By analogy, the origin of synthetic information, we suggest, is the mystery

Optimal and Diffusion Transports in Machine Learning

arXiv:2512.06797v2 Announce Type: replace-cross Abstract: Several problems in machine learning are naturally expressed as the design and analysis of time-evolving probability distributions. This inclu

Our team at @AIatMeta is excited to announce ATLAS: one of the largest automated formalization efforts to date. ATLAS contains Lean 4 formal…

Our team at @AIatMeta is excited to announce ATLAS: one of the largest automated formalization efforts to date. ATLAS contains Lean 4 formalizations of both statements and proofs from 25+ mathematics

researchyann-lecun--x

Path Channels and Plan Extension Kernels: a Mechanistic Description of Planning in a Sokoban RNN

arXiv:2506.10138v3 Announce Type: replace-cross Abstract: We partially reverse-engineer a convolutional recurrent neural network (RNN) trained with model-free reinforcement learning to play the box-pu

PEAR: Equal Area Weather Forecasting on the Sphere

arXiv:2505.17720v3 Announce Type: replace Abstract: Artificial intelligence is rapidly reshaping the natural sciences, with weather forecasting emerging as a flagship AI4Science application where mach

PhAME: Phenotype-Aware Molecular Editing via Latent Diffusion

arXiv:2605.28226v1 Announce Type: new Abstract: Small-molecule drug discovery requires simultaneous optimization of numerous properties of candidate molecules. These properties can be investigated thr

Planning a Community Approach to Diabetes Care in Low- and Middle-Income Countries Using Optimization

arXiv:2305.06426v2 Announce Type: replace Abstract: Diabetes is a global health priority, especially in low- and-middle-income countries, where over 50% of premature deaths are attributed to high bloo

Playing with Words, Improving with Rewards: Training Language Models for Creative Association

arXiv:2605.27832v1 Announce Type: new Abstract: Large Language Models (LLMs) are being applied to increasingly difficult problems and use cases. To navigate their vast solution spaces effectively, LLM

researcharxiv-cs-cl

PLS in the Mirror of Self-Attention

arXiv:2605.28592v1 Announce Type: new Abstract: This note provides an interesting observation on casting partial least square (PLS) as a linearized self-attention so that PLS may be studied within the

Poison with Style: A Practical Poisoning Attack on Code Large Language Models

arXiv:2605.27631v1 Announce Type: cross Abstract: Code Large Language Models (CLLMs) serve as the core of modern code agents, enabling developers to automate complex software development tasks. In thi

Preference-Shaped Expected Hypervolume and R2 Improvement: Exact Computation and Monotonicity

arXiv:2605.28746v1 Announce Type: cross Abstract: This paper studies preference-shaped expected improvement criteria for Bayesian multiobjective optimization. We consider two indicator families which

Prefix-Safe Bayesian Belief Tracking for LLM Reasoning Reliability:Separating Calibration from Ranking

arXiv:2605.27712v1 Announce Type: new Abstract: Long reasoning traces need reliability estimates before final answers are known. We study prefix-conditioned eventual-success estimation, P(y=1 mid o_{1

Privacy Protection Against Personalized Text-to-Image Synthesis via Cross-image Consistency Constraints

arXiv:2504.12747v2 Announce Type: replace Abstract: The rapid advancement of diffusion models and personalization techniques has made it possible to recreate individual portraits from just a few publi

Proper Agnostic Learning of Functions of Halfspaces under Gaussian Marginals

arXiv:2605.27594v1 Announce Type: cross Abstract: We study the problem of computationally efficient proper agnostic learning of multidimensional concept classes under the Gaussian distribution. In thi

Proprio: Latent Self-Scoring and Inference-Time Refinement for Physically Plausible Video Generation

arXiv:2605.28230v1 Announce Type: new Abstract: Modern video generative models produce visually impressive results, yet frequently violate basic physical principles. We propose Proprio, a training-fre

Quantum Machine Learning-based 6G edge Network: Enabling Adaptive Communication and Model Aggregation

arXiv:2605.27417v1 Announce Type: cross Abstract: With the advent of sixth-generation (6G) mobile communication technology, vehicle-to-everything (V2X) communication faces unprecedented challenges in

Quantum principal component analysis without eigenvector recovery

arXiv:2605.27942v1 Announce Type: cross Abstract: Principal component analysis (PCA) is traditionally implemented through a covariance or kernel matrix, leading-eigenvector extraction, and hard rank-k

RCM Constraint-Consistent Dynamic Control in Surgical Robots

arXiv:2509.14075v2 Announce Type: replace Abstract: Robotic-assisted minimally invasive surgery (RAMIS) requires accurate enforcement of the remote center of motion (RCM) constraint to ensure safe too

Real Time NILM Based Power Monitoring of Identical Induction Motors Representing Cutting Machines in Textile Industry

arXiv:2601.01616v2 Announce Type: replace Abstract: The textile industry in Bangladesh is one of the most energy-intensive sectors, yet its monitoring practices remain largely outdated, resulting in i

Realizing Robotic Swimming with Unified Fluid-Robot Multiphysics

arXiv:2506.05012v2 Announce Type: replace Abstract: Matching the swimming efficiency and agility of fish has remained an elusive goal in underwater robotics. Such locomotion capabilities rely on compl

RelaxFlow: Text-Driven Amodal 3D Generation

arXiv:2603.05425v2 Announce Type: replace-cross Abstract: Image-to-3D generation faces inherent semantic ambiguity under occlusion, where partial observation alone is often insufficient to determine o

Residualized Temporal Sparse Autoencoders for Interpreting Diffusion Models

arXiv:2605.27813v1 Announce Type: cross Abstract: Text-to-image diffusion models generate images through an iterative denoising process, so internal neural layers produce trajectories of activations r

Rethinking Calibration for Early-Exit Neural Networks

arXiv:2508.21495v3 Announce Type: replace Abstract: Early-exit neural networks (EENNs) accelerate inference by allowing intermediate classifiers to stop computation once predictions are confident enou

Rethinking Visual Neglect: Steering via Context-Preference for MLLM Hallucination Mitigation

arXiv:2605.27993v1 Announce Type: new Abstract: Object hallucination remains a primary obstacle to the reliable deployment of Multimodal Large Language Models (MLLMs). Current inference-time mitigatio

researcharxiv-cs-cl

REVEAL: Reference-Grounded Reasoning for Multimodal Manipulation Detection

arXiv:2605.28459v1 Announce Type: new Abstract: Multimodal manipulation detection aims to simultaneously identify forged image--text pairs and localize tampered regions, yet existing methods typically

ReverseMath: Answer Inversion for Scalable and Verifiable Mathematical Problem Generation

arXiv:2605.27709v1 Announce Type: new Abstract: Mathematical reasoning benchmarks are vital for evaluating large language models (LLMs), but many are static and repeatedly exposed through public evalu

researcharxiv-cs-cl

Revisiting ML Training under Fully Homomorphic Encryption: Convergence Guarantees, Differential Privacy, and Efficient Algorithms

arXiv:2605.27782v1 Announce Type: new Abstract: We present the first theoretical convergence analysis of machine learning training under fully homomorphic encryption (FHE), combined with a differentia