Search: “safety”

Isotonic Layer: A Unified Framework for Recommendation Calibration and Debiasing

arXiv:2603.06589v2 Announce Type: replace-cross Abstract: Model calibration and debiasing are fundamental yet operationally expensive challenges in large-scale recommendation systems. Existing approac

Jailbreaking Frontier Foundation Models Through Intention Deception

DGX agent

arXiv:2604.24082v1 Announce Type: cross Abstract: Large (vision-)language models exhibit remarkable capability but remain highly susceptible to jailbreaking. Existing safety training approaches aim to

model-releasesarxiv-cs-ai

28 Apr 2026

JSSFF: A Joint Structural-Semantic Fusion Framework for Remote Sensing Image Captioning

arXiv:2604.24031v1 Announce Type: new Abstract: The encoder-decoder framework has become widely popular nowadays. In this model, the encoder extracts informative visual features from an input image, a

K-Score: Kalman Filter as a Principled Alternative to Reward Normalization in Reinforcement Learning

arXiv:2604.23056v1 Announce Type: cross Abstract: We propose a simple yet effective alternative to reward normalization in policy gradient reinforcement learning by integrating a 1D Kalman filter for

KAConvNet: Kolmogorov-Arnold Convolutional Networks for Vision Recognition

arXiv:2604.23320v1 Announce Type: new Abstract: The Convolutional Neural Networks (CNNs) have been the dominant and effective approach for general computer vision tasks. Recently, Kolmogorov-Arnold ne

LAVA: Layered Audio-Visual Anti-tampering Watermarking for Robust Deepfake Detection and Localization

arXiv:2604.23957v1 Announce Type: new Abstract: Proactive watermarking offers a promising approach for deepfake tamper detection and localization in short-form videos. However, existing methods often

Learning from Imperfect Text Guidance: Robust Long-Tail Visual Recognition with High-Noise Label

arXiv:2604.23125v1 Announce Type: new Abstract: Real-world data often exhibit long-tailed distributions with numerous noisy labels, substantially degrading the performance of deep models. While prior

Learning from the Best: Smoothness-Driven Metrics for Data Quality in Imitation Learning

arXiv:2604.23000v1 Announce Type: new Abstract: In behavioral cloning (BC), policy performance is fundamentally limited by demonstration data quality. Real-world datasets contain trajectories of varyi

Learning Human-Intention Priors from Large-Scale Human Demonstrations for Robotic Manipulation

arXiv:2604.24681v1 Announce Type: new Abstract: Human videos contain rich manipulation priors, but using them for robot learning remains difficult because raw observations entangle scene understanding

Learning Selective LLM Autonomy from Copilot Feedback in Enterprise Customer Support Workflows

arXiv:2604.23855v1 Announce Type: new Abstract: We present a deployed system that automates end-to-end customer support workflows inside an enterprise Business Process Management (BPM) platform. The a

Learning to Refine: Self-Refinement of Parallel Reasoning in LLMs

arXiv:2509.00084v2 Announce Type: replace-cross Abstract: Test-time scaling (TTS) has gained widespread attention for enhancing LLM reasoning. Existing approaches such as Best-of-N and majority voting

Learning Under Moral Hazard with Instrumental Regression and Generalized Method of Moments

arXiv:2405.20642v3 Announce Type: replace Abstract: Machine learning has become increasingly popular in informing data-driven policy-making. Policies influence behavior in individuals or populations,

LearnPruner: Rethinking Attention-based Token Pruning in Vision Language Models

arXiv:2604.23950v1 Announce Type: new Abstract: Vision-Language Models (VLMs) have recently demonstrated remarkable capabilities in visual understanding and reasoning, but they also impose significant

Less is More in Semantic Space: Intrinsic Decoupling via Clifford-M for Fundus Image Classification

arXiv:2603.20806v2 Announce Type: replace Abstract: Multi-label fundus diagnosis requires features that capture both fine-grained lesions and large-scale retinal structure. Many multi-scale medical vi

LinguDistill: Recovering Linguistic Ability in Vision-Language Models via Selective Cross-Modal Distillation

arXiv:2604.00829v3 Announce Type: replace-cross Abstract: Adapting pretrained language models (LMs) into vision-language models (VLMs) can degrade their native linguistic capability due to representat

LLMs Reading the Rhythms of Daily Life: Aligned Understanding for Behavior Prediction and Generation

arXiv:2604.23578v1 Announce Type: cross Abstract: Human daily behavior unfolds as complex sequences shaped by intentions, preferences, and context. Effectively modeling these behaviors is crucial for

LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory

arXiv:2603.03269v2 Announce Type: replace Abstract: Feedforward geometric foundation models achieve strong short-window reconstruction, yet scaling them to minutes-long videos is bottlenecked by quadr

Magnetic Indoor Localization through CNN Regression and Rotation Invariance

arXiv:2604.22896v1 Announce Type: cross Abstract: Indoor positioning is an essential technology for a wide range of applications in GNSS-denied environments, including indoor navigation and IoT system

MERIT: Modular Framework for Multimodal Misinformation Detection with Web-Grounded Reasoning

arXiv:2510.17590v2 Announce Type: replace Abstract: We present MERIT, an inference-time modular framework for multimodal misinformation detection that decomposes verification into four specialized mod

Meta-Aligner: Bidirectional Preference-Policy Optimization for Multi-Objective LLMs Alignment

arXiv:2604.24178v1 Announce Type: cross Abstract: Multi-Objective Alignment aims to align Large Language Models (LLMs) with diverse and often conflicting human values by optimizing multiple objectives

MIPIC: Matryoshka Representation Learning via Self-Distilled Intra-Relational and Progressive Information Chaining

arXiv:2604.24374v1 Announce Type: new Abstract: Representation learning is fundamental to NLP, but building embeddings that work well at different computational budgets is challenging. Matryoshka Repr

MIRAGE: A Micro-Interaction Relational Architecture for Grounded Exploration in Multi-Figure Artworks

arXiv:2604.23788v1 Announce Type: new Abstract: Appreciating multi-figure paintings requires understanding how characters relate through subtle cues like gaze alignment, gesture, and spatial arrangeme

Model-Free Inference of Investor Preferences: A Relative Entropy IRL Approach

arXiv:2604.24280v1 Announce Type: new Abstract: We present a framework using Relative Entropy Inverse Reinforcement Learning (RE-IRL) to recover investor reward functions from observed investment acti

MotionHiFlow: Text-to-motion via hierarchical flow matching

arXiv:2604.23264v1 Announce Type: new Abstract: Text-to-motion generation aims to generate 3D human motions that are tightly aligned with the input text while remaining physically plausible and rich i

MTServe: Efficient Serving for Generative Recommendation Models with Hierarchical Caches

arXiv:2604.22881v1 Announce Type: cross Abstract: Generative recommendation (GR) offers superior modeling capabilities but suffers from prohibitive inference costs due to the repeated encoding of long

MultiDx: A Multi-Source Knowledge Integration Framework towards Diagnostic Reasoning

arXiv:2604.24186v1 Announce Type: cross Abstract: Diagnostic prediction and clinical reasoning are critical tasks in healthcare applications. While Large Language Models (LLMs) have shown strong capab

Multimodal Remote Inference

arXiv:2508.07555v3 Announce Type: replace Abstract: We consider a remote inference system with multiple modalities, where a multimodal machine learning (ML) model performs real-time inference using fe

Neural Bridge Processes

arXiv:2508.07220v2 Announce Type: replace-cross Abstract: Learning stochastic functions from partially observed context-target pairs requires models that are expressive, uncertainty-aware, and strongl

OAMVOS:2nd Report for 5th PVUW MOSE Track

arXiv:2604.22837v1 Announce Type: cross Abstract: SAM-based dense trackers provide strong short-term mask propagation but remain fragile under long occlusion, fast motion, viewpoint change, and distra

Omni-o3: Deep Nested Omnimodal Deduction for Deliberative Audio-Visual Reasoning

arXiv:2604.24191v1 Announce Type: new Abstract: Omnimodal understanding entails a massive, highly redundant search space of cross-modal interactions, demanding focused and deliberative reasoning. Curr

One-Shot Real-World Demonstration Synthesis for Scalable Bimanual Manipulation

arXiv:2512.09297v3 Announce Type: replace Abstract: Learning dexterous bimanual manipulation policies critically depends on large-scale, high-quality demonstrations, yet current paradigms face inheren

OpenAI, which squandered its tremendous lead and is now missing its projections, is in trouble. There’s no two ways about it.

OpenAI, which squandered its tremendous lead and is now missing its projections, is in trouble. There’s no two ways about it. 'OpenAI Chief Financial Officer Sarah Friar has told other company leaders

safetygary-marcus--x

Oracle Noise: Faster Semantic Spherical Alignment for Interpretable Latent Optimization

arXiv:2604.23540v1 Announce Type: new Abstract: Text-to-image diffusion models have achieved remarkable generative capabilities, yet accurately aligning complex textual prompts with synthesized layout

Orthogonal Representation Learning for Estimating Causal Quantities

arXiv:2502.04274v4 Announce Type: replace Abstract: End-to-end representation learning has become a powerful tool for estimating causal quantities from high-dimensional observational data, but its eff

Overcoming Copyright Barriers in Corpus Distribution Through Non-Reversible Hashing

arXiv:2604.23412v1 Announce Type: new Abstract: While annotated corpora are crucial in the field of natural language processing (NLP), those containing copyrighted material are difficult to exchange a

Peer Identity Bias in Multi-Agent LLM Evaluation: An Empirical Study Using the TRUST Democratic Discourse Analysis Pipeline

arXiv:2604.22971v1 Announce Type: cross Abstract: The TRUST democratic discourse analysis pipeline exposes its large language model (LLM) components to peer model identity through multiple structural

Personality Shapes Gender Bias in Persona-Conditioned LLM Narratives Across English and Hindi: An Empirical Investigation

arXiv:2604.23600v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed in persona-driven applications such as education, customer service, and social platforms, where m

PhysLayer: Language-Guided Layered Animation with Depth-Aware Physics

arXiv:2604.23574v1 Announce Type: new Abstract: Existing image-to-video generation methods often produce physically implausible motions and lack precise control over object dynamics. While prior appro

POCA: Pareto-Optimal Curriculum Alignment for Visual Text Generation

arXiv:2604.24171v1 Announce Type: new Abstract: Current visual text generation models struggle with the trade-off between text accuracy and overall image coherence. We find that achieving high text ac

Preserving Long-Tailed Expert Information in Mixture-of-Experts Tuning

arXiv:2604.23036v1 Announce Type: cross Abstract: Despite MoE models leading many benchmarks, supervised fine-tuning (SFT) for the MoE architectures remains difficult because its router layers are fra

Probing CLIP's Comprehension of 360-Degree Textual and Visual Semantics

arXiv:2604.24642v1 Announce Type: new Abstract: The dream of instantly creating rich 360-degree panoramic worlds from text is rapidly becoming a reality, yet a crucial gap exists in our ability to rel

Quantifying and Mitigating Self-Preference Bias of LLM Judges

arXiv:2604.22891v1 Announce Type: cross Abstract: LLM-as-a-Judge has become a dominant approach in automated evaluation systems, playing critical roles in model alignment, leaderboard construction, qu

QuietWalk: Physics-Informed Reinforcement Learning for Ground Reaction Force-Aware Humanoid Locomotion Under Diverse Footwear

arXiv:2604.23702v1 Announce Type: new Abstract: Humanoid robots operating in human-centered environments (e.g., homes, hospitals, and offices) must mitigate foot--ground impact transients, as impact-i

Real-Time Non-Contact Force Compensation for Wrist-Mounted Force/Torque Sensors in Haptic-Enabled Robotic Surgery Training

arXiv:2604.23696v1 Announce Type: new Abstract: Haptic feedback has been a long-missed feature in robotic-assisted surgery, one that would allow surgeons to perceive tissue properties and apply contro

RecoverFormer: End-to-End Contact-Aware Recovery for Humanoid Robots

arXiv:2604.22911v1 Announce Type: new Abstract: Humanoid robots operating in unstructured environments must recover from unexpected disturbances-a capability that remains challenging for end-to-end co

Reflective Flow Sampling Enhancement

arXiv:2603.06165v2 Announce Type: replace-cross Abstract: The growing demand for text-to-image generation has led to rapid advances in generative modeling. Recently, text-to-image diffusion models tra

Revisiting On-Policy Distillation: Empirical Failure Modes and Simple Fixes

arXiv:2603.25562v2 Announce Type: replace-cross Abstract: On-policy distillation (OPD) is increasingly used in LLM post-training because it can leverage a teacher model to provide dense supervision on

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis

arXiv:2604.24198v1 Announce Type: cross Abstract: Process Reward Models (PRMs) have achieved remarkable success in augmenting the reasoning capabilities of Large Language Models (LLMs) within static d