arXiv:2603.27044v2 Announce Type: replace-cross Abstract: Deep Reinforcement Learning (DRL) is widely recognized as sample-inefficient, a limitation attributable in part to the high dimensionality and substantial functional redundancy inherent to the policy parameter space. A recent framework, which we refer to as Action-based Policy Compression (APC), mitigates this issue by compressing the parameter space $Theta$ into […]
Ego-Grounding for Personalized Question-Answering in Egocentric Videos
arXiv:2604.01966v1 Announce Type: cross Abstract: We present the first systematic analysis of multimodal large language models (MLLMs) in personalized question-answering requiring ego-grounding – the ability to understand the camera-wearer in egocentric videos. To this end, we introduce MyEgo, the first egocentric VideoQA dataset designed to evaluate MLLMs’ ability to understand, remember, and reason about the […]
Human Misperception of Generative-AI Alignment: A Laboratory Experiment
arXiv:2502.14708v3 Announce Type: replace-cross Abstract: We conduct an incentivized laboratory experiment to study people’s perception of generative artificial intelligence (GenAI) alignment in the context of economic decision-making. Using a panel of economic problems spanning the domains of risk, time preference, social preference, and strategic interactions, we ask human subjects to make choices for themselves and […]
Bias Is a Subspace, Not a Coordinate: A Geometric Rethinking of Post-hoc Debiasing in Vision-Language Models
arXiv:2511.18123v2 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) have become indispensable for multimodal reasoning, yet their representations often encode and amplify demographic biases, resulting in biased associations and misaligned predictions in downstream tasks. Such behavior undermines fairness and distorts the intended alignment between vision and language. Recent post-hoc approaches attempt to mitigate bias by replacing […]
The Silicon Mirror: Dynamic Behavioral Gating for Anti-Sycophancy in LLM Agents
arXiv:2604.00478v2 Announce Type: replace Abstract: Large Language Models (LLMs) increasingly prioritize user validation over epistemic accuracy – a phenomenon known as sycophancy. We present The Silicon Mirror, an orchestration framework that dynamically detects user persuasion tactics and adjusts AI behavior to maintain factual integrity. Our architecture introduces three components: (1) a Behavioral Access Control (BAC) […]
Bayesian inference of mixed Gaussian phylogenetic models
arXiv:2410.11548v3 Announce Type: replace Abstract: Background: Continuous traits evolution of a group of taxa that are correlated through a phylogenetic tree is commonly modelled using parametric stochastic differential equations to represent deterministic change of trait through time, while incorporating noises that represent different unobservable evolutionary pressures. Often times, a heterogeneous Gaussian process that consists of […]
V-OCBF: Learning Safety Filters from Offline Data via Value-Guided Offline Control Barrier Functions
arXiv:2512.10822v2 Announce Type: replace Abstract: Ensuring safety in autonomous systems requires controllers that aim to satisfy state-wise constraints without relying on online interaction.While existing Safe Offline RL methods typically enforce soft expected-cost constraints, they struggle to ensure strict state-wise safety. Conversely, Control Barrier Functions (CBFs) offer a principled mechanism to enforce forward invariance, but often […]
PhysGaia: A Physics-Aware Benchmark with Multi-Body Interactions for Dynamic Novel View Synthesis
arXiv:2506.02794v2 Announce Type: replace-cross Abstract: We introduce PhysGaia, a novel physics-aware benchmark for Dynamic Novel View Synthesis (DyNVS) that encompasses both structured objects and unstructured physical phenomena. While existing datasets primarily focus on photorealistic appearance, PhysGaia is specifically designed to support physics-consistent dynamic reconstruction. Our benchmark features complex scenarios with rich multi-body interactions, where objects […]
Beyond Preset Identities: How Agents Form Stances and Boundaries in Generative Societies
arXiv:2603.23406v2 Announce Type: replace Abstract: While large language models simulate social behaviors, their capacity for stable stance formation and identity negotiation during complex interventions remains unclear. To overcome the limitations of static evaluations, this paper proposes a novel mixed-methods framework combining computational virtual ethnography with quantitative socio-cognitive profiling. By embedding human researchers into generative multiagent […]
Generalized Machine Learning for Fast Calibration of Agent-Based Epidemic Models
arXiv:2509.07013v3 Announce Type: replace-cross Abstract: Agent-based models (ABMs) are widely used to study infectious disease dynamics, but their calibration is often computationally intensive, limiting their applicability in time-sensitive public health settings. We propose DeepIMC (Deep Inverse Mapping Calibration), a machine learning-based calibration framework that directly learns the inverse mapping from epidemic time series to epidemiological […]
PBLean: Pseudo-Boolean Proof Certificates for Lean 4
arXiv:2602.08692v2 Announce Type: replace-cross Abstract: We present PBLean, a method for importing VeriPB pseudo-Boolean (PB) proof certificates into Lean 4. Key to our approach is reflection: a Boolean checker function whose soundness is fully proved in Lean and executed as compiled native code. Our method scales to proofs with tens of thousands of steps that […]
Do Phone-Use Agents Respect Your Privacy?
arXiv:2604.00986v2 Announce Type: replace-cross Abstract: We study whether phone-use agents respect privacy while completing benign mobile tasks. This question has remained hard to answer because privacy-compliant behavior is not operationalized for phone-use agents, and ordinary apps do not reveal exactly what data agents type into which form entries during execution. To make this question measurable, […]