safety

Offline Reinforcement Learning for Warehouse SLAM Throughput Control

arXiv:2606.23978v1 Announce Type: cross Abstract: We present an offline reinforcement learning (RL) framework for optimizing SLAM throughput control in a warehouse fulfillment environment. SLAM (Scan/

On the Smallness of the Large Language Models Scaling Exponents

DGX agent

arXiv:2606.24504v1 Announce Type: new Abstract: We discuss reasons why the scaling exponents of current Large Language Models (LLMs) applications are indicating an unsustainable regime in terms of ene

safetyarxiv-cs-ai

24 Jun 2026

One Year Later...The Harms Persist, But So Do We!

arXiv:2606.23884v1 Announce Type: cross Abstract: General-purpose large language models (LLMs) are increasingly used for mental health-related conversations, yet safety safeguards remain inadequate an

PHANTOM: A Large-Scale Dataset of Multimodal Adversarial Attacks for Vision-Language Models

arXiv:2606.24388v1 Announce Type: new Abstract: We introduce a large-scale, open-source dataset of pre-generated adversarial attacks for vision-language models (VLMs). The dataset is designed to be di

PixJail: Self-Evolving Paper-to-Pipeline Reproduction for Text-to-Image Jailbreak Evaluation

arXiv:2606.24081v1 Announce Type: cross Abstract: As Text-to-Image (T2I) jailbreak techniques evolve rapidly, existing benchmarks and reproduction workflows often struggle to keep pace. More important

Please watch this looney tunes ass video on this wiki page https://en.wikipedia.org/wiki/Hypergolic_propellant

Hypergolic propellants are rocket fuels that spontaneously ignite when their components come into contact without requiring an external ignition source, making them useful for spacecraft propulsion sy

safetyconnor-leahy--x

Policies Permitting LLM Use for Polishing Peer Reviews Are Currently Not Enforceable

arXiv:2603.20450v2 Announce Type: replace-cross Abstract: A number of scientific conferences and journals have recently enacted policies that prohibit LLM usage by peer reviewers, except for polishing

Policy Gradient with Self-Attention for Model-Free Distributed Nonlinear Multi-Agent Games

arXiv:2509.18371v2 Announce Type: replace-cross Abstract: Multi-agent games in dynamic nonlinear settings are challenging due to the time-varying interactions among the agents and the non-stationarity

Progressive Alignment Objectives for Aligner-Encoder based ASR

arXiv:2606.24147v1 Announce Type: cross Abstract: Aligner-Encoders are recently proposed seq2seq end-to-end ASR models that replace decoder attention by predicting the uth token directly from the u-th

safetyarxiv-cs-cl

Quant Convergence: Bridging Classical Value Investing and Modern Factor Models for Systematic Equity Selection

arXiv:2606.24575v1 Announce Type: new Abstract: Modern finance relies heavily on complex machine learning models to find patterns in the stock market. However, as these AI models get more complicated,

Real vs. Complex Spectral Bases for Neural Operators: The Role of Green's Function Alignment

arXiv:2606.24851v1 Announce Type: new Abstract: Fourier Neural Operators (FNO) learn solution operators of partial differential equations by parameterizing global convolutions in the complex Fourier d

Red-Teaming the Agentic Red-Team

arXiv:2606.24496v1 Announce Type: cross Abstract: The use of agentic systems to perform offensive security operations has moved from a theoretical possibility to a commoditized capability. However, wh

Reinforcement Learning for Computer-Use Agents with Autonomous Evaluation

arXiv:2606.24515v1 Announce Type: new Abstract: Computer-Use Agents (CUAs) execute high-level user goals by perceiving and acting directly within graphical user interfaces. However, reinforcement lear

Reinforcement Learning Towards Broadly and Persistently Beneficial Models

arXiv:2606.24014v1 Announce Type: new Abstract: As AI systems are deployed across increasingly diverse and high-stakes settings, model alignment must generalize beyond the tasks and domains seen durin

Rethinking Structural Anomaly Detection: From Decision Boundaries to Projection Operators

arXiv:2606.15280v2 Announce Type: replace Abstract: Most existing anomaly detection methods rely on estimating a probability density or learning an enclosing decision boundary, implicitly assuming tha

RoBoSR: Structured Scene Representations for Embodied Robotic Reasoning

arXiv:2606.24338v1 Announce Type: new Abstract: Despite rapid progress, embodied reasoning under real-world variability remains challenging. Existing approaches rely on demonstration-driven sequential

RTFF: Random-to-Target Fabric Flattening Policy using Dual-Arm Manipulator

arXiv:2510.00814v2 Announce Type: replace Abstract: Robotic fabric manipulation remains challenging due to fabric deformability and occlusions from wrinkles and the manipulator. This paper defines Ran

Safe and Generalizable Hierarchical Multi-Agent RL via Constraint Manifold Control

arXiv:2606.24010v1 Announce Type: new Abstract: Multi-agent systems are widely used in safety-critical applications that require coordinated behavior under strict safety constraints. Existing approach

SC3-Eval: Evaluating Robot Foundation Models via Self-Consistent Video Generation

arXiv:2606.18610v2 Announce Type: replace-cross Abstract: Evaluating generalist robot manipulation policies in the real world is expensive, slow, and difficult to scale. Action-conditioned video world

ScaleToT: Generalizing Structured LLM Reasoning for Billion-Scale Low-Activity User Modeling

arXiv:2606.24605v1 Announce Type: new Abstract: Accurate user modeling often depends on rich interaction histories, which are unavailable for billions of low-activity users. Large Language Models (LLM

SEAL: Searching Expandable Architectures for Incremental Learning

arXiv:2505.10457v3 Announce Type: replace-cross Abstract: Incremental learning is a machine learning paradigm where a model learns from a sequential stream of tasks. This setting poses a key challenge

Selective Capability Unlearning in End-to-End Spoken Language Understanding

arXiv:2606.24063v1 Announce Type: cross Abstract: Modern spoken language understanding (SLU) systems are increasingly deployed in real-world settings, where specific functionalities may need to be rem

Similarity of Neural Network Representations in Superposition

arXiv:2604.00208v2 Announce Type: replace Abstract: Comparing internal representations is a central goal in neuroscience and machine learning, but standard linear alignment metrics (Representational S

Social Structure Matters in 3D Human-Human Interaction Generation

arXiv:2606.24255v1 Announce Type: cross Abstract: Although text-to-motion generation has achieved strong progress in synthesizing realistic single-person motions from language, extending it to text-dr

Societal Alignment Frameworks Can Improve LLM Alignment

arXiv:2503.00069v2 Announce Type: replace-cross Abstract: Recent progress in large language models (LLMs) has focused on producing responses that meet human expectations and align with shared values -

SPACE: Enabling Learning from Cross-Robot Data Toward Generalist Policies

arXiv:2606.24049v1 Announce Type: new Abstract: In robot learning, scaling training datasets across diverse embodiments and environments has become a dominant paradigm for learning generalizable robot

Spectral Evolution-Guided Token Pruning in Multimodal Large Language Models

arXiv:2606.24165v1 Announce Type: new Abstract: Reducing visual token redundancy is critical for accelerating Multimodal Large Language Models (MLLMs) without degrading cross-modal reasoning performan

Statistical Foundations of LLM-based A/B Testing: A Surrogacy Framework for Human Causal Inference

arXiv:2606.17165v3 Announce Type: replace-cross Abstract: Organizations and researchers show increasing interest in using large language models (LLMs) in place of human participants in A/B tests, in t

TACTFUL: Tactile-Driven Exploration For Object Localization and Identification in Confined Environments

arXiv:2606.24712v1 Announce Type: cross Abstract: Humans effortlessly locate and identify objects by touch alone, even without vision. In contrast, robotic systems rely heavily on vision and struggle

“The Al bubble is by far the biggest stock-market bubble that mankind has ever seen - both in scale and scope, in terms of the leverage that…

“The Al bubble is by far the biggest stock-market bubble that mankind has ever seen - both in scale and scope, in terms of the leverage that's in there and in terms of the sheer excessive exuberance t

The problem we face with AI today is not a technical problem, it is a political problem. Of who gets to decide. What level of risk the publi…

The problem we face with AI today is not a technical problem, it is a political problem. Of who gets to decide. What level of risk the public is exposed to, what future we build towards or avert. It's

safetyconnor-leahy--x

The world of computing is and will remain far larger, more impactful, and far more vibrant than the narrow subdomain of genAI.

Gary Marcus argues that generative AI, while significant, represents only a narrow subset of the broader computing field and should not overshadow the diverse and impactful work occurring across other

Themis: An explainable AI-enabled framework for Reinforcement Learning with Human Feedback

arXiv:2606.24622v1 Announce Type: new Abstract: Training safe Reinforcement Learning (RL) systems is inherently challenging, with no guarantee of avoiding unwanted behaviors. The most effective defens

Today I present you a curated collection of @tszzl saying that Fukuyama is always right

Today I present you a curated collection of @tszzl saying that Fukuyama is always right We Need an International Treaty to Ban Superintelligence https://open.substack.com/pub/persuasion1/p/time-for-a-

safetyconnor-leahy--x

Token-to-Token Alignment of Text Embeddings for Semantic Blending

arXiv:2606.24021v1 Announce Type: new Abstract: In modern generative models, images are specified and controlled through text prompts. In practice, images are generated from sequences of tokens derive

TruncProof: A Guardrail for LLM-based JSON Generation under Token-Length Constraints

arXiv:2605.13076v2 Announce Type: replace Abstract: The LLM-based generation of machine-readable outputs such as JSON has attracted significant attention for integration with external systems. However

safetyarxiv-cs-cl

UniTranslator: A Unified Multi-modal Framework for End-to-end In-Image Machine Translation

arXiv:2606.24333v1 Announce Type: new Abstract: In-Image Machine Translation (IIMT) aims to translate scene text in an image and render the translated text back into the original regions while preserv

UOL@IDEM at BEA 2026 Shared Task 1: Neural Fusion and Feature-Rich Modeling for L1-Aware Vocabulary Difficulty Prediction

arXiv:2606.24501v1 Announce Type: new Abstract: This paper describes UOL@IDEM's closed-track submission to the BEA 2026 shared task on L1-aware vocabulary difficulty prediction. We model the task as r

safetyarxiv-cs-cl

Verifiable Foundation Models for Robot Safety

arXiv:2606.23754v1 Announce Type: cross Abstract: Deploying foundation models for robot control raises a central challenge: the expressive power that enables rich, multimodal perception also makes the

Welcome to the GenerativeAI Fizzle™

This post likely references Gary Marcus's critical commentary on limitations or failures in generative AI systems, using 'Fizzle' as a metaphorical or literal descriptor for underperformance or unmet

What Do Flow-Based Inverse Solvers Approximate? A Posterior-Transport View

arXiv:2606.24516v1 Announce Type: new Abstract: A growing family of training-free solvers -- FlowDPS, FLOWER, PnP-Flow and their diffusion ancestors (DPS, DAPS) -- repurpose a pretrained flow-matching

When AI Meets Finance (StockAgent): Large Language Model-based Stock Trading in Simulated Real-world Environments

arXiv:2407.18957v5 Announce Type: replace-cross Abstract: Can AI Agents simulate real-world trading environments to investigate the impact of external factors on stock trading activities (e.g., macroe

When CQs Go Wrong: Challenges in CQ Verification with OE-Assist

arXiv:2606.24619v1 Announce Type: new Abstract: Competency Questions (CQs) are the central component of CQ-verification, an established process in which an ontology is evaluated against a set of natur

When Preferences Fail to Become Incentives: A Utility-Behavior Gap in Large Language Models

arXiv:2606.22974v2 Announce Type: replace Abstract: Recent work on preference elicitation in large language models (LLMs) has demonstrated that, when given a series of choices between two outcomes, LL

Wow even @MicahLasher thinks the OpenAI-Andreessen-Palantir money spent to oppose @AlexBores backfired --

Wow even @MicahLasher thinks the OpenAI-Andreessen-Palantir money spent to oppose @AlexBores backfired -- NY-12 retrospective in the NYT from Teddy Schleifer. Hard to imagine this was the headline tha

360Anything: Geometry-Free Lifting of Images and Videos to 360{eg}

arXiv:2601.16192v2 Announce Type: replace Abstract: Lifting perspective images and videos to 360{eg} panoramas enables immersive 3D world generation. Existing approaches often rely on explicit geometr

23 Jun 2026

A Controlled Study of CLIP-Based Body-Scene Fusion for Emotion Recognition in Context

arXiv:2606.22072v1 Announce Type: new Abstract: Apparent emotion in natural images is often not visible from the face alone. The face may be small, hidden, or neutral, while posture and scene context

23 Jun 2026

A Generative Model for Closed-Loop Microsimulation of Signalized Intersections

arXiv:2606.23588v1 Announce Type: new Abstract: Traffic microsimulators rely on hand-crafted behavior models that reproduce aggregate flow but miss the heterogeneous interactions between vehicles at s