safety

HeraSys: Collaborative Serving of Multiple LLM Workflows via Fine-Grained End-to-End Optimization

arXiv:2607.22578v1 Announce Type: new Abstract: The proliferation of Large Language Models (LLMs) has shifted serving systems from processing isolated requests to orchestrating high-concurrency, multi

Safety

Hierarchical Soft Actor-Critic for Sparse-Reward Long-Horizon Reinforcement Learning

DGX agent

arXiv:2607.23726v1 Announce Type: cross Abstract: Exploration in sparse-reward long-horizon tasks poses significant challenges for reinforcement learning. To address these challenges, we propose a two

safetyarxiv-cs-lg

28 Jul 2026

How LLM Task-Adaptation Reshapes Alignment: A Multi-dimensional Study of Behavioral and Representational Drift

arXiv:2607.22676v1 Announce Type: new Abstract: Post-training is a key mechanism for adapting large language models to downstream tasks. While prior work suggests that task adaptation can alter a mode

Hybrid AI-Physical Modeling for Penetration Bias Correction in X-band InSAR DEMs: A Greenland Case Study

arXiv:2504.08909v2 Announce Type: replace Abstract: Digital elevation models derived from Interferometric Synthetic Aperture Radar (InSAR) data over glacial and snow-covered regions often exhibit syst

IJCB-AFMFR 2026: Competition on Adapting Foundation Models for Face Recognition Using Synthetic Training Data

arXiv:2607.24422v1 Announce Type: new Abstract: This paper presents a summary of the Competition on Adapting Foundation Models for Face Recognition Using Synthetic Training Data (AFMFR), held at the 2

Improving Adversarial Robustness of Zero-Shot CLIP with Confidence-Aware Weighting

arXiv:2510.02913v2 Announce Type: replace Abstract: Vision-language models such as CLIP demonstrate impressive zero-shot generalization but remain highly vulnerable to adversarial attacks. Prior adver

In-Context Learning as Implicit Policy Gradient

arXiv:2607.23153v1 Announce Type: cross Abstract: Recent work has shown that large language models (LLMs) can iteratively improve their outputs by incorporating generated samples and their correspondi

Infrared Imaging Empowered by Artificial Intelligence for Pediatric Skeletal Triage: A Narrative Review and Future Perspectives

arXiv:2607.24727v1 Announce Type: new Abstract: Background. Pediatric musculoskeletal trauma represents up to 18% of pediatric ED visits, yet diagnosis still depends on ionizing radiography. Cumulativ

Intent-Governed Tool Authorization for AI Agents

arXiv:2606.22916v2 Announce Type: replace Abstract: AI agents increasingly act through external tools: they read private data, construct structured payloads, submit write requests, export records, and

InterOCF: Spatio-Temporal 2D-3D Interaction for Camera-Only 4D Occupancy Forecasting

arXiv:2607.24431v1 Announce Type: new Abstract: Camera-only 4D occupancy forecasting enables autonomous vehicles to predict future 3D semantic scenes solely from historical multi-view images, which is

KAI: A Kinematic-Aware Interface for Data-Efficient Articulated Object Manipulation

arXiv:2607.24493v1 Announce Type: new Abstract: Articulated object manipulation requires an understanding of kinematic structure that is difficult and costly to learn from robot demonstrations alone.

KAP: Bridging the Knowledge Selection-Runtime Consumption Gap in LLM Systems

arXiv:2607.24260v1 Announce Type: new Abstract: Modern LLM systems increasingly rely on knowledge-selection processes that produce high-value structured priors, such as ranked evidence, graph topology

Knowledge-Guided Cross-Modal Fusion for Adult-to-Pediatric ECG Transfer via Label-Conditioned Contrastive Alignment

arXiv:2607.15928v2 Announce Type: replace Abstract: Adult and pediatric electrocardiogram (ECG) interpretation relies on age-sensitive criteria, and models pretrained mainly on adult ECGs often transf

LeapBot-WA: World-Anchor Action Models via Predictive Latent Alignments

arXiv:2607.23969v1 Announce Type: new Abstract: World Action Models (WAMs) have emerged as a powerful paradigm for embodied intelligence, yet the prevailing reliance on pixel-level video generation cr

Learning Adaptive Multi-Task Guidance, Navigation, and Control via Hypernetworks

arXiv:2607.24292v1 Announce Type: new Abstract: Autonomous free-flying robots in orbital environments require controllers that are both versatile and resource-efficient, yet maintaining a separate, ta

Learning Reusable Hybrid Motion Priors for Humanoid Locomotion from Motion Imitation

arXiv:2607.24083v1 Announce Type: new Abstract: Reinforcement learning can produce robust humanoid controllers, but each new task is typically trained as a separate policy with its own reward design a

LLM-Based Scientific Equation Discovery via Physics-Informed Token-Regularized Policy Optimization

arXiv:2602.10576v2 Announce Type: replace-cross Abstract: Symbolic regression aims to distill mathematical equations from observational data. Recent approaches have successfully leveraged Large Langua

Long-Tailed Medical Image Classification

arXiv:2607.23883v1 Announce Type: new Abstract: In this paper, we examine the difficulties of using standard techniques for medical image classification due to long-tailed distributions (wherein rarer

LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget

arXiv:2607.14952v3 Announce Type: replace Abstract: Long-context RL post-training is constrained by the lifetime of state and gradients, not attention cost alone. In GRPO, one multi-million-token prom

Looping Is Not Reliability: State-Bound Evidence and Typed Revision Contracts for Agentic Code Repair

arXiv:2607.24604v1 Announce Type: cross Abstract: Generate--test--revise loops are common in coding agents, but repetition alone provides no reliability guarantee. We study the gap between finding a c

LuxInstruct: A Cross-Lingual Instruction Tuning Dataset For Luxembourgish

arXiv:2510.07074v2 Announce Type: replace-cross Abstract: Instruction tuning has become a key technique for enhancing the performance of large language models, enabling them to better follow human pro

Making Mathematical Knowledge Explainable, Accessible and Interoperable Through Large Language Model Integration

arXiv:2607.24512v1 Announce Type: new Abstract: Mathematical models are central to formalizing research problems, yet their documentation often falls short of FAIR principles. Knowledge bases such as

MedDDC-Eval: Diagnosis-Decoupled Evaluation of Multi-Turn Medical Consultation Agents

arXiv:2607.18999v2 Announce Type: replace-cross Abstract: Evaluating multi-turn medical consultation agents requires judging the diagnostic support provided by the histories they elicit through intera

MemChain: Learning Interpretable Memory Traces for Memory-Augmented LLM Agents

arXiv:2607.24097v1 Announce Type: new Abstract: Memory-augmented LLM agents typically answer queries by retrieving relevant memories and feeding them directly to an answer model. This retrieval-as-evi

MEMENTO: Memory-Guided Memetic Code-as-Policy Evolution

arXiv:2607.22832v1 Announce Type: new Abstract: Long-horizon embodied tasks require policies that execute many dependent actions before task success can be observed. Representing policies as executabl

MemTX: Transactional Belief Commit for Stateful Agent Memory

arXiv:2607.23929v1 Announce Type: new Abstract: LLM agents increasingly coordinate through persistent shared memory: one agent's write becomes another agent's premise, and eventually a tool call with

MIME: Multimodal Interactive Motion Encoder

arXiv:2607.22702v1 Announce Type: new Abstract: Text-motion representation learning has advanced rapidly, with growing interest in multi person interactions for animation, AR/VR, and embodied AI. Thes

Mission-Level Runtime Assurance for LLM-Assisted ISR Swarms over a Verification-Aware Fabric

arXiv:2607.23532v1 Announce Type: cross Abstract: Swarms of LLM-assisted autonomous robots are increasingly proposed for cooperative intelligence, surveillance, and reconnaissance (ISR) in contested e

MobiWave: Dispatch-Oriented Graph Wavelets and Drift-Guided Selective Optimization for Autonomous Fleet Rebalancing

arXiv:2607.24365v1 Announce Type: new Abstract: Autonomous fleets enable mobility platforms to coordinate idle vehicles directly, making fleet-wide rebalancing possible. However, two obstacles limit r

Moral Hazard in Multi-Agent Language Models

arXiv:2607.23982v1 Announce Type: cross Abstract: Cooperation can fail when socially valuable effort is costly, weakly observable, and mainly benefits others. Drawing on Holmstrom's team moral-hazard

MS-GPT: Rethinking MS/MS De Novo Structure Elucidation as Spectrum-Induced Posterior Querying of a Molecule-Language Model

arXiv:2607.23607v1 Announce Type: cross Abstract: Molecular structure elucidation from tandem mass spectra (MS/MS) is a central inverse problem in analytical chemistry. Most existing approaches to MS/

safetyarxiv-cs-cl

Multi-Modal Object Re-Identification with Prompt-S6 and Semantic-Aware Knowledge Guidance

arXiv:2607.23451v1 Announce Type: new Abstract: Multi-modal object Re-Identification (ReID) aims to retrieve specific objects by integrating complementary information from multiple modalities. However

Multi-Task GRPO: Reliable LLM Reasoning Across Tasks

arXiv:2602.05547v2 Announce Type: replace-cross Abstract: RL-based post-training with GRPO is widely used to improve large language models on individual reasoning tasks. However, real-world deployment

Multimodal Domain Generalization for Depression Detection: An Attention-Based BiLSTM Network with Domain-Adversarial Training

arXiv:2607.22794v1 Announce Type: cross Abstract: Automatic depression detection with deep learning has shown promise but often suffers from limited generalization due to domain shift arising from int

Mutual Modality Trust with Lightweight Reconstruction Regularization for Fine-grained Tire Pattern Recognition

arXiv:2607.23979v1 Announce Type: new Abstract: Visual tire recognition serves as a core supporting technique for vehicle safety monitoring, autonomous driving perception and automated automotive main

N_0-VTLA: Scaling Vision-Tactile-Language-Action Model with Latent Tactile Tokens

arXiv:2607.23782v1 Announce Type: new Abstract: We present N_0-VTLA, a vision-tactile-language-action (VTLA) foundation model capable of (1) fine-grained contact-rich manipulation with tactile percept

NeurGO: Learning to Generate Elite Candidates for Meta-Black-Box Expensive Optimization

arXiv:2607.23408v1 Announce Type: new Abstract: Expensive black-box optimization is ubiquitous in science and engineering, where function evaluations are costly and the evaluation budget is limited. T

Neuro-Symbolic Meta-Policies for Temporal Knowledge-Graph Memory under Partial Observability

arXiv:2607.18368v2 Announce Type: replace Abstract: Partially observable reinforcement learning requires deciding what to retain, retrieve, and forget over time. We introduce a neuro-symbolic meta-pol

OmniVAE: An Audio-Video VAE with Cross-Modal Alignment for Joint Generation

arXiv:2607.23855v1 Announce Type: cross Abstract: Recent generative models are moving beyond silent video or standalone audio synthesis toward the joint generation of synchronized audio and video. Des

On AI Safety and Security Technical Debt in Engineering AI-Enabled Systems

arXiv:2607.23365v1 Announce Type: cross Abstract: Artificial intelligence (AI) systems are increasingly deployed in high-stakes domains such as healthcare, autonomous driving, finance, and education.

Online Policy Evaluation for MDPs with Dynamic UBSR Measures

arXiv:2607.23030v1 Announce Type: new Abstract: Developing efficient function-approximation methods for policy evaluation is a fundamental challenge in risk-aware reinforcement learning. Existing appr

Open weights let builders own and control their stack, and provide flexibility to optimized quality and performance, instead of being locked…

Open weights let builders own and control their stack, and provide flexibility to optimized quality and performance, instead of being locked into a handful of closed platforms. We think that choice is

safetytogether-ai--x

Open Your Model's Eyes: Video and Context-Aware Multimodal Backchannel Prediction

arXiv:2607.22729v1 Announce Type: cross Abstract: Backchannels, which signal listener states like empathy and understanding, are fundamental to natural human interaction. However, current approaches r

safetyarxiv-cs-cl

Optimal Reward Shaping: Autonomous Car Parking Case Study

arXiv:2607.23617v1 Announce Type: new Abstract: Designing effective reward functions for model-free reinforcement learning under non-holonomic constraints remains a persistent challenge, often resulti

Outcome-Confounded Local Supervision in On-Policy Distillation

arXiv:2607.23731v1 Announce Type: new Abstract: On-policy distillation (OPD) trains a student on its own trajectories while a teacher supplies dense token-level likelihoods at student-visited prefixes

Outcome-Fair Restless Multi-Armed Bandits for Stochastic Deadline Scheduling

arXiv:2607.23772v1 Announce Type: cross Abstract: We study a restless multi-armed bandit (RMAB) problem for a stochastic deadline scheduling application. RMAB problems are solved using the Whittle ind

Parallel Tokenizers: Rethinking Encoder Models' Vocabulary Design in Cross-Lingual Transfer of Low-Resource Languages

arXiv:2510.06128v2 Announce Type: replace Abstract: Tokenization forms the basis of multilingual language models, yet existing methods often limit cross-lingual transfer by mapping semantically equiva

safetyarxiv-cs-cl

Perturbation-Aware Diffusion-Guided Hybrid Segmentation for Robust and Annotation-Efficient Plant Stress Phenotyping

arXiv:2607.23680v1 Announce Type: new Abstract: Semantic segmentation in agricultural imagery is often evaluated under in-domain protocols, yet practical deployment requires robustness to appearance p