arXiv:2603.22121v1 Announce Type: cross Abstract: Text-driven video moment retrieval (VMR) remains challenging due to limited capture of hidden temporal dynamics in untrimmed videos, leading to imprecise grounding in long sequences. Traditional methods rely on natural language queries (NLQs) or static image augmentations, overlooking motion sequences and suffering from high computational costs in Transformer-based architectures. Existing […]
ThinkJEPA: Empowering Latent World Models with Large Vision-Language Reasoning Model
arXiv:2603.22281v1 Announce Type: cross Abstract: Recent progress in latent world models (e.g., V-JEPA2) has shown promising capability in forecasting future world states from video observations. Nevertheless, dense prediction from a short observation window limits temporal context and can bias predictors toward local, low-level extrapolation, making it difficult to capture long-horizon semantics and reducing downstream utility. […]
Can synthetic data reproduce real-world findings in epidemiology? A replication study using adversarial random forests
arXiv:2508.14936v2 Announce Type: replace Abstract: Synthetic data holds substantial potential to address practical challenges in epidemiology due to restricted data access and privacy concerns. However, many current methods suffer from limited quality, high computational demands, and complexity for non-experts. Furthermore, common evaluation strategies for synthetic data often fail to directly reflect statistical utility and measure […]
Social Comparison without Explicit Inference of Others’ Reward Values: A Constructive Approach Using a Probabilistic Generative Model
arXiv:2512.18687v4 Announce Type: replace Abstract: Social comparison$unicodex2014$the process of evaluating one’s rewards relative to others$unicodex2014$is an essential feature of social emotions such as envy and plays a fundamental role in primate social cognition. However, it remains unknown how information about others’ rewards affects one’s own reward valuation. This study examines whether monkeys merely recognize objective […]
Benchmarking Zero-Shot Reasoning Approaches for Error Detection in Solidity Smart Contracts
arXiv:2603.13239v2 Announce Type: replace Abstract: Smart contracts play a central role in blockchain systems by encoding financial and operational logic. Still, their susceptibility to subtle security flaws poses significant risks of financial loss and erosion of trust. LLMs create new opportunities for automating vulnerability detection, yet the effectiveness of different prompting strategies and model choices […]
Imaging foundation model for universal enhancement of non-ideal measurement CT
arXiv:2410.01591v3 Announce Type: replace-cross Abstract: Non-ideal measurement computed tomography (NICT) employs suboptimal imaging protocols to expand CT applications. However, the resulting trade-offs degrade image quality, limiting clinical acceptability. Although deep learning methods have been used to enhance NICT images, their reliance on large training datasets and limited generalizability across diverse settings hinder practical use. We […]
Must Read: A Comprehensive Survey of Computational Persuasion
arXiv:2505.07775v2 Announce Type: replace-cross Abstract: Persuasion is a fundamental aspect of communication, influencing decision-making across diverse contexts, from everyday conversations to high-stakes scenarios such as politics, marketing, and law. The rise of conversational AI systems has significantly expanded the scope of persuasion, introducing both opportunities and risks. AI-driven persuasion can be leveraged for beneficial applications, […]
Chain of Retrieval: Multi-Aspect Iterative Search Expansion and Post-Order Search Aggregation for Full Paper Retrieval
arXiv:2507.10057v3 Announce Type: replace-cross Abstract: Scientific paper retrieval, particularly framed as document-to-document retrieval, aims to identify relevant papers in response to a long-form query paper, rather than a short query string. Previous approaches to this task have focused exclusively on abstracts, embedding them into dense vectors as surrogates for full documents and calculating similarity between […]
GEM: A Native Graph-based Index for Multi-Vector Retrieval
arXiv:2603.20336v1 Announce Type: cross Abstract: In multi-vector retrieval, both queries and data are represented as sets of high-dimensional vectors, enabling finer-grained semantic matching and improving retrieval quality over single-vector approaches. However, its practical adoption is held back by the lack of effective indexing algorithms. Existing work, attempting to reuse standard single-vector indexes, often fails to […]
Flowception: Temporally Expansive Flow Matching for Video Generation
arXiv:2512.11438v2 Announce Type: replace-cross Abstract: We present Flowception, a novel non-autoregressive and variable-length video generation framework. Flowception learns a probability path that interleaves discrete frame insertions with continuous frame denoising. Compared to autoregressive methods, Flowception alleviates error accumulation/drift as the frame insertion mechanism during sampling serves as an efficient compression mechanism to handle long-term context. […]
CurES: From Gradient Analysis to Efficient Curriculum Learning for Reasoning LLMs
arXiv:2510.01037v2 Announce Type: replace-cross Abstract: Curriculum learning plays a crucial role in enhancing the training efficiency of large language models (LLMs) on reasoning tasks. However, existing methods often fail to adequately account for variations in prompt difficulty or rely on simplistic filtering mechanisms to select prompt datasets within a narrow criterion range, resulting in significant […]
Why Agent Caching Fails and How to Fix It: Structured Intent Canonicalization with Few-Shot Learning
arXiv:2602.18922v2 Announce Type: replace-cross Abstract: Personal AI agents incur substantial cost via repeated LLM calls. We show existing caching methods fail: GPTCache achieves 37.9% accuracy on real benchmarks; APC achieves 0-12%. The root cause is optimizing for the wrong property — cache effectiveness requires key consistency and precision, not classification accuracy. We observe cache-key evaluation […]