arXiv:2603.24963v2 Announce Type: replace Abstract: Modern computational advertising platforms typically rely on recommendation systems to predict user responses, such as click-through rates, conversion rates, and other optimization events. To support a wide variety of product surfaces and advertiser goals, these platforms frequently maintain an extensive ecosystem of machine learning (ML) models. However, operating at this […]
ImagenWorld: Stress-Testing Image Generation Models with Explainable Human Evaluation on Open-ended Real-World Tasks
arXiv:2603.27862v1 Announce Type: cross Abstract: Advances in diffusion, autoregressive, and hybrid models have enabled high-quality image synthesis for tasks such as text-to-image, editing, and reference-guided composition. Yet, existing benchmarks remain limited, either focus on isolated tasks, cover only narrow domains, or provide opaque scores without explaining failure modes. We introduce textbfImagenWorld, a benchmark of 3.6K […]
Efficient Mixture-of-Expert for Video-based Driver State and Physiological Multi-task Estimation in Conditional Autonomous Driving
arXiv:2410.21086v3 Announce Type: replace-cross Abstract: Road safety remains a critical challenge worldwide, with approximately 1.35 million fatalities annually attributed to traffic accidents, often due to human errors. As we advance towards higher levels of vehicle automation, challenges still exist, as driving with automation can cognitively over-demand drivers if they engage in non-driving-related tasks (NDRTs), or […]
Is Seeing Believing? Evaluating Human Sensitivity to Synthetic Video
arXiv:2603.13846v3 Announce Type: replace-cross Abstract: Advances in machine learning have enabled the creation of realistic synthetic videos known as deepfakes. As deepfakes proliferate, concerns about rapid spread of disinformation and manipulation of public perception are mounting. Despite the alarming implications, our understanding of how individuals perceive synthetic media remains limited, obstructing the development of effective […]
Symbolic Analysis of Grover Search Algorithm via Chain-of-Thought Reasoning and Quantum-Native Tokenization
arXiv:2505.04880v2 Announce Type: replace-cross Abstract: Understanding the high-level conceptual structure of quantum algorithms from their low-level circuit representations is a critical task for verification, debugging, and education. While traditional numerical simulators can calculate output probabilities, they do not explicitly surface the underlying algorithmic logic, such as the function of an oracle or embedded symmetries. In […]
A Semi Centralized Training Decentralized Execution Architecture for Multi Agent Deep Reinforcement Learning in Traffic Signal Control
arXiv:2512.04653v2 Announce Type: replace-cross Abstract: Multi-agent reinforcement learning (MARL) has emerged as a promising paradigm for adaptive traffic signal control (ATSC) of multiple intersections. Existing approaches typically follow either a fully centralized or a fully decentralized design. Fully centralized approaches suffer from the curse of dimensionality, and reliance on a single learning server, whereas purely […]
Multi-View Attention Multiple-Instance Learning Enhanced by LLM Reasoning for Cognitive Distortion Detection
arXiv:2509.17292v2 Announce Type: replace-cross Abstract: Cognitive distortions have been closely linked to mental health disorders, yet their automatic detection remained challenging due to contextual ambiguity, co-occurrence, and semantic overlap. We proposed a novel framework that combines Large Language Models (LLMs) with Multiple-Instance Learning (MIL) architecture to enhance interpretability and expression-level reasoning. Each utterance was decomposed […]
ControlGUI: Guiding Generative GUI Exploration through Perceptual Visual Flow
arXiv:2502.03330v3 Announce Type: replace-cross Abstract: During the early stages of interface design, designers need to produce multiple sketches to explore a design space. Design tools often fail to support this critical stage, because they insist on specifying more details than necessary. Although recent advances in generative AI have raised hopes of solving this issue, in […]
ProofBridge: Auto-Formalization of Natural Language Proofs in Lean via Joint Embeddings
arXiv:2510.15681v3 Announce Type: replace-cross Abstract: Translating human-written mathematical theorems and proofs from natural language (NL) into formal languages (FLs) like Lean 4 has long been a significant challenge for AI. Most state-of-the-art methods either focus on theorem-only NL-to-FL auto-formalization or on FL proof synthesis from FL theorems. In practice, auto-formalization of both theorem and proof […]
Efficient Tree-Structured Deep Research with Adaptive Resource Allocation
arXiv:2510.05145v2 Announce Type: replace-cross Abstract: Deep research agents, which synthesize information across diverse sources, are significantly constrained by the sequential nature of reasoning. This bottleneck results in high latency, poor runtime adaptability, and inefficient resource allocation, making today’s deep research systems impractical for interactive applications. To overcome this, we introduce ParallelResearch, a novel framework for […]
UniGame: Turning a Unified Multimodal Model Into Its Own Adversary
arXiv:2511.19413v3 Announce Type: replace-cross Abstract: Unified Multimodal Models (UMMs) have shown impressive performance in both understanding and generation with a single architecture. However, UMMs still exhibit a fundamental inconsistency: understanding favors compact embeddings, whereas generation favors reconstruction-rich representations. This structural trade-off produces misaligned decision boundaries, degraded cross-modal coherence, and heightened vulnerability under distributional and adversarial […]
Stepwise Credit Assignment for GRPO on Flow-Matching Models
arXiv:2603.28718v1 Announce Type: cross Abstract: Flow-GRPO successfully applies reinforcement learning to flow models, but uses uniform credit assignment across all steps. This ignores the temporal structure of diffusion generation: early steps determine composition and content (low-frequency structure), while late steps resolve details and textures (high-frequency details). Moreover, assigning uniform credit based solely on the final […]