Measuring and Detecting Harmful AI Sycophancy
arXiv:2608.05624v1 Announce Type: new Abstract: Sycophantic responses are becoming pervasive in large language models (LLMs), and prior work has pointed out that some of them could be harmful. This pa
Knowledge catalogue
arXiv:2608.05624v1 Announce Type: new Abstract: Sycophantic responses are becoming pervasive in large language models (LLMs), and prior work has pointed out that some of them could be harmful. This pa
arXiv:2608.05371v1 Announce Type: new Abstract: World models learn latent states that summarize interaction histories, evolve over time, and support prediction, simulation, or planning. Most existing
arXiv:2511.20633v2 Announce Type: replace Abstract: Vision-Language-Action (VLA) policies excel in aligning language, perception, and robot control. However, most VLAs are trained purely by imitation,
arXiv:2608.06211v1 Announce Type: cross Abstract: Significant advancements in deep learning have been made possible by the utilization of large datasets, underscoring the critical importance of copyri
arXiv:2608.06259v1 Announce Type: new Abstract: Reaction yield prediction remains challenging because labeled data are scarce and reaction space is both combinatorially large and sparsely populated, l
arXiv:2608.05710v1 Announce Type: new Abstract: When an AI system is deployed, the individuals who use and or are evaluated by it form beliefs about how the system operates and use those beliefs to st
arXiv:2608.05705v1 Announce Type: cross Abstract: Deep learning is a new way for machinery fault diagnosis but requires extensive labeled data, a scarce resource in industrial settings. We propose Spe
arXiv:2608.05416v1 Announce Type: new Abstract: Can nonlinear dynamical systems be learned through a compact linear state-space representation, without directly solving a non-convex system-identificat
arXiv:2608.05774v1 Announce Type: new Abstract: Joint-embedding predictive architectures learn by predicting latent representations of missing observations, yet many masked JEPAs are evaluated primari
arXiv:2602.14265v3 Announce Type: replace Abstract: Inference-Time-Compute (ITC) methods like Best-of-n and Tree-of-Thoughts are meant to produce output candidates that are both high-quality and diver
arXiv:2608.06276v1 Announce Type: cross Abstract: Persistence diagrams (PDs) provide stable and interpretable summaries of multiscale topological structure. While substantial progress has been made in
arXiv:2608.05455v1 Announce Type: new Abstract: When a student must learn concepts connected by prerequisite dependencies, when does the order of instruction matter, and what does it cost to find the
arXiv:2608.05215v1 Announce Type: cross Abstract: Learning manipulation skills from human videos is promising for scalable robot learning. However, the embodiment mismatch between humans and robots ma
Go beyond chat in the GitHub Copilot app with these slash commands. They'll help you plan, collaborate, automate, and customize your dev workflow. The post A guide to slash commands in the GitHub Copi
arXiv:2608.04616v1 Announce Type: new Abstract: An information theory-based framework is proposed in attempt to explain insistence on sameness in autism as an instance of a general behavior pattern in
As engineering teams adopt coding agents like Codex, leaders need visibility into adoption, consumption, and reliability. This post shows how to route Codex OpenTelemetry metrics through a local colle
Learn how to configure rate limits on Amazon Bedrock AgentCore gateway to enforce per-user and per-target traffic controls. Define request, token, and connection limits scoped by JWT claims or IAM ide
arXiv:2608.04737v1 Announce Type: new Abstract: Direct Time-of-Flight (dToF) sensors provide highly accurate metric depth and are more robust than indirect ToF systems in challenging real-world condit
August is here, bringing 26 new games for GeForce NOW members. Command the seas in World of Warships: Legends and discover what’s next in the GeForce NOW library, starting with the eight newly added g
arXiv:2608.04827v1 Announce Type: cross Abstract: We introduce the Intrinsic Hybrid Latent Diffusion Model (ILDM), a generative framework that integrates probabilistic dimensionality reduction with ge
arXiv:2607.18559v2 Announce Type: replace-cross Abstract: Gaussian graphical model selection is usually studied under independent sampling, but in many applications the data arise as a single trajecto
arXiv:2608.04358v1 Announce Type: new Abstract: Continual learning (CL) requires models to learn tasks sequentially, yet deep neural networks often suffer from plasticity loss and poor knowledge trans
arXiv:2608.04381v1 Announce Type: cross Abstract: Self-supervised learning on graphs is largely shaped by contrastive methods that depend on carefully designed augmentations, and by generative methods
arXiv:2608.04060v1 Announce Type: cross Abstract: Joint-embedding predictive architectures learn abstract states by predicting target embeddings from context embeddings, but their transition models ar
arXiv:2608.04075v1 Announce Type: cross Abstract: Accurate traffic forecasting is essential for proactive resource management in edge computing, where service demand evolves dynamically across both sp
arXiv:2608.04676v1 Announce Type: new Abstract: Surgical procedures unfold as structured and recurring clinical events, whose real-time understanding via intraoperative surgical videos is critical for
arXiv:2608.04285v1 Announce Type: new Abstract: Neurosymbolic AI systems that integrate machine learning and symbolic reasoning are rapidly gaining attention. They complement the data-intensive statis
arXiv:2409.02228v2 Announce Type: replace-cross Abstract: When language models (LMs) are trained to forget (or 'unlearn'') a skill, how precisely does their behavior change? We study the behavior of t
arXiv:2608.05069v1 Announce Type: cross Abstract: Video Anomaly Detection (VAD) is inherently challenging due to the scarcity of anomalies and the large visual variability in surveillance footage, inc
arXiv:2608.04820v1 Announce Type: new Abstract: Face inpainting with diffusion models has recently achieved impressive visual quality, yet preserving identity fidelity under significant occlusion and
arXiv:2505.02915v2 Announce Type: replace Abstract: Tactile sensing is an important sensing modality for robot manipulation. Among different types of tactile sensors, magnet-based sensors, like u-skin
arXiv:2608.01432v2 Announce Type: replace Abstract: Artificial general intelligence (AGI) may weaken scarcities in labour, expertise, information, and productive capability that underpin established t
arXiv:2608.03999v1 Announce Type: cross Abstract: Text-to-music language models begin with a choice usually made by default: how to tokenize music. Normally entangled with backbone, data, and recipe,
arXiv:2608.02679v1 Announce Type: cross Abstract: Collaborative AI experimentation across industry and academia requires platforms that enable rapid prototyping while preserving controlled access, ten
Announcing Discovery Loop! I am very excited to announce that, along with my longtime friends and collaborators @Sanjay_Ghemawat, @OriolVinyalsML and @quocleix, we are founding Discovery Loop (@DiscoL
arXiv:2608.03085v1 Announce Type: cross Abstract: Causal inference has traditionally centered on scalar outcomes: whether a patient recovers, how much a worker earns, or how many visits a website rece
arXiv:2608.03185v1 Announce Type: new Abstract: Focal cortical dysplasia (FCD) type II is an important structural cause of drug-resistant focal epilepsy, but its small size, heterogeneous appearance,
arXiv:2608.03025v1 Announce Type: new Abstract: Multimodal named entity recognition (MNER) determines whether each candidate span and entity-type hypothesis is supported by joint textual and visual ev
arXiv:2608.03566v1 Announce Type: cross Abstract: The drift diffusion model (DDM) is a cornerstone of cognitive decision-making research. Although numerous estimation methods exist, researchers contin
arXiv:2608.03260v1 Announce Type: new Abstract: Pretraining has shown strong potential for learning transferable representations, yet it remains underexplored for electron-density-based molecular lear
arXiv:2608.03498v1 Announce Type: new Abstract: Federated Learning (FL) enables collaborative model training across distributed healthcare institutions without centralising sensitive patient data. How
arXiv:2608.03118v1 Announce Type: new Abstract: This innovative practice full paper describes an AI-powered knowledge graph platform that connects SQL errors to conceptual gaps in undergraduate and gr
arXiv:2608.03295v1 Announce Type: new Abstract: Recent data-driven methods for synthesizing 6-DoF grasp poses use generative models to learn complex grasp pose distributions and generate diverse candi
arXiv:2608.03517v1 Announce Type: new Abstract: Codebook-driven generative compression uses a pretrained image or video generator as a zero-shot visual prior and transmits compact codebook indices to
arXiv:2608.03556v1 Announce Type: new Abstract: Soft wearable robots have evolved rapidly from proof-of-concept devices into promising platforms for rehabilitation, occupational assistance, and human
arXiv:2608.02697v1 Announce Type: cross Abstract: Attribution methods (AMs) assign an importance score to each feature and are widely adopted to explain black-box models. However, most methods can pro
arXiv:2511.20532v3 Announce Type: replace-cross Abstract: The primary output of the nervous system is movement and behavior. While recent advances have democratized pose tracking during complex behavi
arXiv:2608.02993v1 Announce Type: new Abstract: (Flat) Reinforcement Learning (RL) agents face significant challenges in environments with sparse rewards that require long-horizon reasoning. A compell
arXiv:2608.02762v1 Announce Type: new Abstract: Fine-grained wildlife classification in aerial imagery is limited not only by model performance, but also by unreliable labels: animals occupy few pixel
arXiv:2608.02887v1 Announce Type: new Abstract: Choosing which features to collect is a deployment decision: the same limited questionnaire, test panel, or sensor set may need to serve several heterog
arXiv:2608.03937v1 Announce Type: new Abstract: Overlapped friction ridge patterns are a recurring problem in latent fingerprints recovered from crime scenes and in live-scan scenarios where residual
arXiv:2608.03069v1 Announce Type: new Abstract: Deep Q-Networks (DQNs) learn value functions through bootstrapped temporal-difference updates, where future returns are approximated using a greedy maxi
arXiv:2608.03550v1 Announce Type: new Abstract: Chain-of-Thought (CoT) prompting remains the standard baseline for evaluating models' reasoning abilities. Originally, this technique was introduced to
arXiv:2608.03913v1 Announce Type: cross Abstract: Dense pretrained transformers do not naturally expose interpretable units for circuit extraction. Existing approaches obtain such units by learning au
arXiv:2602.16611v3 Announce Type: replace-cross Abstract: Humans can infer material characteristics of objects from their visual appearance, and this ability extends to artistic depictions, where simi
arXiv:2608.03276v1 Announce Type: new Abstract: Long-context inference with large language models is constrained by the linear growth of the key-value cache to sequence length. While pruning offers mi
Two weeks ago, I resigned from OpenAI to join Conduit as a founding researcher, where we're training models to non-invasively read the human mind. I've written some thoughts about what telepathy could
arXiv:2608.02160v1 Announce Type: new Abstract: In this paper, we propose a characteristic-aware adaptive network named AdaForensics for deepfake detection. Most existing methods learn a fixed network
arXiv:2608.01252v1 Announce Type: new Abstract: Catastrophic forgetting is a major problem in task-incremental learning, where neural networks tend to overwrite previously learned knowledge when train
arXiv:2608.02455v1 Announce Type: new Abstract: Human-centered assessment tasks, which are essential for systematic decision-making, rely heavily on human judgment and typically lack verifiable ground