arXiv:2510.26575v1 Announce Type: cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) is a promising approach for enhancing agentic deep search. However, its application is often hindered by low textbfReward Density in deep search scenarios, where agents expend significant exploratory costs for infrequent and often null final rewards. In this paper, we formalize this challenge as […]
SPLite Hand: Sparsity-Aware Lightweight 3D Hand Pose Estimation
arXiv:2510.16396v3 Announce Type: replace-cross Abstract: With the increasing ubiquity of AR/VR devices, the deployment of deep learning models on edge devices has become a critical challenge. These devices require real-time inference, low power consumption, and minimal latency. Many framework designers face the conundrum of balancing efficiency and performance. We design a light framework that adopts […]
On the limitation of evaluating machine unlearning using only a single training seed
arXiv:2510.26714v1 Announce Type: cross Abstract: Machine unlearning (MU) aims to remove the influence of certain data points from a trained model without costly retraining. Most practical MU algorithms are only approximate and their performance can only be assessed empirically. Care must therefore be taken to make empirical comparisons as representative as possible. A common practice […]
Advancing Mobile GUI Agents: A Verifier-Driven Approach to Practical Deployment
arXiv:2503.15937v4 Announce Type: replace Abstract: We propose V-Droid, a mobile GUI task automation agent. Unlike previous mobile agents that utilize Large Language Models (LLMs) as generators to directly generate actions at each step, V-Droid employs LLMs as verifiers to evaluate candidate actions before making final decisions. To realize this novel paradigm, we introduce a comprehensive […]
Think Then Embed: Generative Context Improves Multimodal Embedding
arXiv:2510.05014v3 Announce Type: replace Abstract: There is a growing interest in Universal Multimodal Embeddings (UME), where models are required to generate task-specific representations. While recent studies show that Multimodal Large Language Models (MLLMs) perform well on such tasks, they treat MLLMs solely as encoders, overlooking their generative capacity. However, such an encoding paradigm becomes less […]
Constrained Posterior Sampling: Time Series Generation with Hard Constraints
arXiv:2410.12652v2 Announce Type: replace-cross Abstract: Generating realistic time series samples is crucial for stress-testing models and protecting user privacy by using synthetic data. In engineering and safety-critical applications, these samples must meet certain hard constraints that are domain-specific or naturally imposed by physics or nature. Consider, for example, generating electricity demand patterns with constraints on […]
Toward a Public and Secure Generative AI: A Comparative Analysis of Open and Closed LLMs
arXiv:2505.10603v2 Announce Type: replace-cross Abstract: Generative artificial intelligence (Gen AI) systems represent a critical technology with far-reaching implications across multiple domains of society. However, their deployment entails a range of risks and challenges that require careful evaluation. To date, there has been a lack of comprehensive, interdisciplinary studies offering a systematic comparison between open-source and […]
Human-assisted Robotic Policy Refinement via Action Preference Optimization
arXiv:2506.07127v3 Announce Type: replace-cross Abstract: Establishing a reliable and iteratively refined robotic system is essential for deploying real-world applications. While Vision-Language-Action (VLA) models are widely recognized as the foundation model for such robotic deployment, their reliance on offline expert demonstrations critically limits their capacity for post-deployment refinement. To mitigate this limitation, we introduce Action Preference […]
Holographic Transformers for Complex-Valued Signal Processing: Integrating Phase Interference into Self-Attention
arXiv:2509.19331v2 Announce Type: replace-cross Abstract: Complex-valued signals encode both amplitude and phase, yet most deep models treat attention as real-valued correlation, overlooking interference effects. We introduce the Holographic Transformer, a physics-inspired architecture that incorporates wave interference principles into self-attention. Holographic attention modulates interactions by relative phase and coherently superimposes values, ensuring consistency between amplitude and […]
The Structure of Relation Decoding Linear Operators in Large Language Models
arXiv:2510.26543v1 Announce Type: cross Abstract: This paper investigates the structure of linear operators introduced in Hernandez et al. [2023] that decode specific relational facts in transformer language models. We extend their single-relation findings to a collection of relations and systematically chart their organization. We show that such collections of relation decoders can be highly compressed […]