safety

Bilevel Data Curation for LLM Fine-tuning: Offline Selection and Online Self-Refining Generation

arXiv:2511.21056v2 Announce Type: replace-cross Abstract: Supervised fine-tuning (SFT) datasets are critical to the downstream performance of large language models, yet they often contain low-quality

Safety

bit-equivalent on-policy rl for glm-5.2 has been achieved internally developing…

DGX agent

I cannot provide an accurate summary of this entry as the title appears incomplete and the URL/source information seems corrupted or mismatched (the handle doesn't match the URL). To create a reliable

safetysonya-huang--x

24 Jun 2026

Boosting Text-Driven Video Segmentation via Geometry-Aware Distillation

arXiv:2606.24464v1 Announce Type: new Abstract: Text-driven Referring Video Object Segmentation (RVOS) aims to locate and segment target objects in videos given natural language. However, existing mod

Breaking Shortcut Learning for Cross-Trial EEG-Guided Target Speech Extraction via Two-Stage Training

arXiv:2606.24164v1 Announce Type: cross Abstract: Recent end-to-end models for EEG-guided target speech extraction report impressive results, underscoring potential for neuro-steered hearing technolog

Breaking the Filter Bubble: A Semantic Pareto-DQN Framework for Multi-Objective Recommendation

arXiv:2606.24042v1 Announce Type: new Abstract: Recommender systems often induce filter bubbles and semantic homogenization by monolithically optimizing for immediate user engagement. Standard single-

Breaking the Mirror: Activation-Based Mitigation of Self-Preference in LLM Evaluators

arXiv:2509.03647v2 Announce Type: replace-cross Abstract: Large language models (LLMs) increasingly serve as automated evaluators, yet they suffer from 'self-preference bias': a tendency to favor thei

Bridging the Manifold Gap: Riemannian Residual Line Search for One-Step Image Editing

arXiv:2606.24844v1 Announce Type: new Abstract: One-step diffusion editors are fast because they avoid inversion and iterative optimization, but a single transport update must be aggressive enough to

CALIBER: Calibrating Confidence Before and After Reasoning in Language Models

arXiv:2606.24281v1 Announce Type: cross Abstract: Reasoning language models are increasingly asked not only to answer difficult questions, but also to estimate their likelihood of success. Existing me

COMPANY BUILT ON IP THEFT RAGES AGAINST THEFT OF ITS OWN IP

COMPANY BUILT ON IP THEFT RAGES AGAINST THEFT OF ITS OWN IP ANTHROPIC ACCUSED ALIBABA OF UNAUTHORIZED ACCESS TO ITS AI MODELS, OUTLINING ITS ALLEGATIONS IN LETTERS SENT TO U.S. SENATORS AND THE WHITE

safetygary-marcus--x

Congresswoman denies staff used AI to write defense funding amendment

Rep. Anna Paulina Luna (R-FL) says her staff used AI for 'spellcheck' in an amendment summary for a major defense bill, but denies it was used for the bill text itself and says 'NO Legislation is ever

safetythe-verge-ai

Critique of Agent Model

arXiv:2606.23991v1 Announce Type: new Abstract: What is an agent? What constitutes agency? With the rise of Large Language Model (LLM) systems marketed as ``coding agents'', ``AI co-scientists'', and

Cryptographic certificates of validity for trustworthy AI

arXiv:2606.23768v1 Announce Type: cross Abstract: We propose cryptographic certificates of validity for agentic AI systems. The core idea is to formally specify a correctness or policy condition as a

DDStereo: Efficient Dual Decoder Transformers for Stereo 3D Road Anomaly Detection

arXiv:2606.24805v1 Announce Type: new Abstract: Stereo-based 3D object detection still faces two critical safety challenges: real-time performance and open-set generalization. Existing stereo 3D metho

Decentralized SGD with Controlled Disagreement Finds Flatter Minima

arXiv:2602.02899v2 Announce Type: replace Abstract: Decentralized training is often regarded as inferior to centralized training because the consensus errors between workers are thought to undermine c

DREG: A Layer-Wise Jacobian Regularization as a General-Purpose Penalty

arXiv:2606.23942v1 Announce Type: new Abstract: We present a large-scale empirical study isolating the contributions of the Derivative Regularization penalty (DREG). Across a fully-crossed factorial s

DriveStack-VLA: Render-Teacher Alignment for BEV-Based DeepStack Vision-Language-Action Model

arXiv:2606.24051v1 Announce Type: new Abstract: Vision-Language-Action driving models convert a pretrained Vision-Language Model into a driving policy, allowing them to use world knowledge and follow

Dynamic Symmetric Point Tracking: Tackling Non-ideal Reference in Analog In-memory Training

arXiv:2602.21321v2 Announce Type: replace Abstract: Analog in-memory computing (AIMC) performs computation directly within resistive crossbar arrays, offering an energy-efficient platform to scale lar

Enabling Robust Cloth Manipulation via Inference-Time Simulator-in-the-Loop Refinement

arXiv:2606.24552v1 Announce Type: new Abstract: Simulator-in-the-loop optimization offers a promising inference-time mechanism for robot manipulation. It uses a physical simulator as a backend rollout

Enforcing Human-like Kinematics in Dexterous Piano Playing via Adversarial Posture Regularization

arXiv:2606.23848v1 Announce Type: new Abstract: Reinforcement learning can train bimanual dexterous hands to play piano in physics simulation with high note accuracy, but for high-DoF dexterous hands,

Escaping the Self-Confirmation Trap: An Execute-Distill-Verify Paradigm for Agentic Experience Learning

arXiv:2606.24428v1 Announce Type: new Abstract: Experience-driven self-evolution is critical for large language model (LLM) agents to improve through open-world interaction. However, existing experien

Evaluating the Interpretability of Sparse Autoencoders with Concept Annotations

arXiv:2606.24716v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) are increasingly used to extract interpretable concepts from vision and vision language models, yet existing evaluation met

EvidenceLens: A Claim-Evidence Matrix for Auditing Financial Question Answering

arXiv:2606.23724v1 Announce Type: cross Abstract: Large language models are increasingly used to answer questions over annual reports, earnings decks, and analyst notes, yet their outputs remain diffi

EXPO-SQL: Execution-based Clause-level Policy Optimization for Text-to-SQL

arXiv:2606.23693v1 Announce Type: new Abstract: Text-to-SQL enables users to query databases using natural language by generating executable SQL queries. Recent methods have increasingly adopted Large

FALCON: Transforming Cyber Threat Intelligence into Deployable IDS Rules with Self-Reflection

arXiv:2508.18684v2 Announce Type: replace-cross Abstract: Signature-based Intrusion Detection Systems (IDS) detect malicious activity by matching network or host events against predefined rules. Secur

FlowR2A: Learning Reward-to-Action Distribution for Multimodal Driving Planning

arXiv:2606.24231v1 Announce Type: new Abstract: Multimodal driving planning faces a long-standing tension between two paradigms: scoring-based methods benefit from dense reward supervision but are con

From 'Aha Moments' to Controllable Thinking: Toward Meta-Cognitive Reasoning in Large Reasoning Models via Decoupled Reasoning and Control

arXiv:2508.04460v2 Announce Type: replace Abstract: Large Reasoning Models (LRMs) can exhibit step-by-step reasoning, reflection, and backtracking, but these behaviors are often unregulated, leading t

From Local Corrections to Generalized Skills: Improving Neuro-Symbolic Policies with MEMO

arXiv:2603.04560v2 Announce Type: replace Abstract: Recent works use a neuro-symbolic framework for general manipulation policies. The advantage of this framework is that -- by applying off-the-shelf

FT-WBC: Learning Fault-Tolerant Whole-Body Control for Legged Loco-Manipulation

arXiv:2606.24466v1 Announce Type: new Abstract: Legged manipulators combine the mobility of legged platforms with the manipulation capability of robotic arms. However, arm-induced Center-of-Mass shift

G^3VLA: Geometric inductive bias for Vision-Language-Action Models

arXiv:2606.24472v1 Announce Type: cross Abstract: Vision-language-action (VLA) models have made rapid progress in generalist robot manipulation by harnessing semantic knowledge from pretrained vision-

GENA3D: Generative Amodal 3D Modeling by Bridging 2D Priors and 3D Coherence

arXiv:2511.21945v3 Announce Type: replace Abstract: Generating complete 3D objects under partial occlusions (i.e., amodal scenarios) is a practically important yet challenging problem, as large portio

Generative Manifold Distillation: Aligning Restoration Trajectories with Natural Image Prior

arXiv:2512.11121v2 Announce Type: replace Abstract: Pre-trained image restoration models often fail on out-of-distribution (OOD) real-world degradations. Adapting to these domains is challenging as re

Geometric Action Model for Robot Policy Learning

arXiv:2606.17046v2 Announce Type: replace-cross Abstract: Generalist robot policies must follow user instructions while reasoning about how objects, cameras, and robot actions interact in the 3D physi

Governed Shared Memory for Multi-Agent LLM Systems

arXiv:2606.24535v1 Announce Type: new Abstract: Multi-agent LLM environments require robust mechanisms for shared knowledge management. This paper formalizes the fleet-memory problem and identifies fo

Hierarchical Spatial and Channel Aggregation for Cross-domain Few-shot Segmentation

arXiv:2606.24296v1 Announce Type: new Abstract: Cross-domain Few-shot Segmentation (CD-FSS) aims to learn generalizable segmentation capability from abundant annotated samples in the source domain, en

HiPath: Hierarchical Vision-Language Alignment for Structured Pathology Report Prediction

arXiv:2603.19957v2 Announce Type: replace-cross Abstract: Pathology reports are structured, multi-granular documents encoding diagnostic conclusions, histological grades, and ancillary test results ac

Hybrid Sequence Modeling and Reinforced Verification for Controllable Target-Conditioned Decision Making

arXiv:2508.16420v3 Announce Type: replace Abstract: Target-conditioned sequence models provide a simple interface for controllable offline decision making, but the requested target return can be an un

JEDEL: Zero-Shot DNA-Encoded Library Design for Early-Stage Drug Discovery

arXiv:2606.23745v1 Announce Type: cross Abstract: We present JEDEL, a framework for generating synthesis-ready DNA-encoded libraries (DELs) directly from three-dimensional pharmacophore representation

KLip-PPO: A per-sample KL perspective on PPO-Clip

arXiv:2606.23932v1 Announce Type: new Abstract: Proximal Policy Optimization (PPO) is the standard policy-gradient algorithm for on-policy reinforcement learning. The literature presents it in two for

Latent Visual States for Efficient Multimodal Reasoning

arXiv:2606.24233v1 Announce Type: new Abstract: The integration of visual evidence has significantly enhanced the capabilities of large multimodal models. However, this integration predominantly relie

LecturaAgents: A Multi-Agent Framework for Adaptive Personalized AI-Assisted Learning and Embodied Teaching

arXiv:2606.16428v2 Announce Type: replace-cross Abstract: Effective personalized AI-assisted learning demands systems that can not only generate accurate learner-specific educational materials, but al

Less is More: Quality-Aware Training Data Selection for Scientific Summarization

arXiv:2606.24828v1 Announce Type: new Abstract: Scientific long-document summarization datasets commonly treat author-written abstracts as gold reference summaries, although their quality and alignmen

Light-weight Pronunciation Assessment via Discrete Speech Token Surprisal

arXiv:2606.19910v2 Announce Type: replace Abstract: Training automated pronunciation assessment often relies on labeled learner errors or non-native corpora that are costly to collect. We propose a li

Lightweight Test-Time Adaptation for EMG-Based Gesture Recognition

arXiv:2601.04181v2 Announce Type: replace Abstract: Reliable long-term decoding of gestures from surface electromyography (EMG) is hindered by signal drift caused by electrode displacement, muscle fat

Listening makes Vision Clear for VLMs

arXiv:2606.23763v1 Announce Type: cross Abstract: Recent work typically assesses vision--language consistency using attention distributions of answer-side tokens. However, we observe that highest atte

looking forward to the GenAI sequel https://www.everyoneislying.com

Gary Marcus expresses anticipation for developments in generative AI, suggesting continued evolution and advancement in the field. The post likely discusses expectations for next-generation AI capabil

safetygary-marcus--x

Military branches restore flu shot requirement after virus swept through base

After Secretary of Defense Pete Hegseth ended the military's flu shot mandate in April 2026, a major flu outbreak struck Lackland Air Force Base in Texas , with at least 222 recruits diagnosed with th

safetyars-technica

MSPL: Multi-Step Pseudo-Labeling for Open-Vocabulary Object Detection

arXiv:2510.14792v4 Announce Type: replace Abstract: Open-vocabulary object detection (OVD) aims to recognize and localize object categories beyond the training set. Recent approaches leverage vision-l

Multi-agent imitation learning with function approximation: Linear Markov games and beyond

arXiv:2602.22810v2 Announce Type: replace Abstract: In this work, we present the first theoretical analysis of multi-agent imitation learning (MAIL) in linear Markov games where both the transition dy