arXiv:2511.22153v2 Announce Type: replace-cross Abstract: The widespread adoption of large language models (LLMs) has made it difficult to distinguish human writing from machine-produced text in many real applications. Detectors that were effective for one generation of models tend to degrade when newer models or modified decoding strategies are introduced. In this work, we study this […]
Exploiting Spatiotemporal Properties for Efficient Event-Driven Human Pose Estimation
arXiv:2512.06306v1 Announce Type: cross Abstract: Human pose estimation focuses on predicting body keypoints to analyze human motion. Event cameras provide high temporal resolution and low latency, enabling robust estimation under challenging conditions. However, most existing methods convert event streams into dense event frames, which adds extra computation and sacrifices the high temporal resolution of the […]
Asymptotic analysis of shallow and deep forgetting in replay with Neural Collapse
arXiv:2512.07400v1 Announce Type: cross Abstract: A persistent paradox in continual learning (CL) is that neural networks often retain linearly separable representations of past tasks even when their output predictions fail. We formalize this distinction as the gap between deep feature-space and shallow classifier-level forgetting. We reveal a critical asymmetry in Experience Replay: while minimal buffers […]
TimeScope: Towards Task-Oriented Temporal Grounding In Long Videos
arXiv:2509.26360v3 Announce Type: replace-cross Abstract: Identifying key temporal intervals within long videos, known as temporal grounding (TG), is important to video understanding and reasoning tasks. In this paper, we introduce a new form of the temporal grounding problem, textbfTask-oriented Temporal Grounding (textbfToTG), which is driven by the requirements of downstream tasks rather than explicit time-interval […]
Latent Collaboration in Multi-Agent Systems
arXiv:2511.20639v2 Announce Type: replace-cross Abstract: Multi-agent systems (MAS) extend large language models (LLMs) from independent single-model reasoning to coordinative system-level intelligence. While existing LLM agents depend on text-based mediation for reasoning and communication, we take a step forward by enabling models to collaborate directly within the continuous latent space. We introduce LatentMAS, an end-to-end training-free […]
Beyond Markovian: Reflective Exploration via Bayes-Adaptive RL for LLM Reasoning
arXiv:2505.20561v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) trained via Reinforcement Learning (RL) have exhibited strong reasoning capabilities and emergent reflective behaviors, such as rethinking and error correction, as a form of in-context exploration. However, the Markovian policy obtained from conventional RL training does not give rise to reflective exploration behaviors since the policy […]
Learning to Use AI for Learning: Teaching Responsible Use of AI Chatbot to K-12 Students Through an AI Literacy Module
arXiv:2508.13962v2 Announce Type: replace-cross Abstract: As Artificial Intelligence (AI) becomes increasingly integrated into daily life, there is a growing need to equip the next generation with the ability to apply, interact with, evaluate, and collaborate with AI systems responsibly. Prior research highlights the urgent demand from K-12 educators to teach students the ethical and effective […]
FinWorld: An All-in-One Open-Source Platform for End-to-End Financial AI Research and Deployment
arXiv:2508.02292v2 Announce Type: replace Abstract: Financial AI holds great promise for transforming modern finance, with the potential to support a wide range of tasks such as market forecasting, portfolio management, quantitative trading, and automated analysis. However, existing platforms remain limited in task coverage, lack robust multimodal data integration, and offer insufficient support for the training […]
Deep Learning Meets Mechanism Design: Key Results and Some Novel Applications
arXiv:2401.05683v2 Announce Type: replace-cross Abstract: Mechanism design is essentially reverse engineering of games and involves inducing a game among strategic agents in a way that the induced game satisfies a set of desired properties in an equilibrium of the game. Desirable properties for a mechanism include incentive compatibility, individual rationality, welfare maximisation, revenue maximisation (or […]
Information Physics of Intelligence: Unifying Logical Depth and Entropy under Thermodynamic Constraints
arXiv:2511.19156v3 Announce Type: replace-cross Abstract: The rapid scaling of artificial intelligence models has revealed a fundamental tension between model capacity (storage) and inference efficiency (computation). While classical information theory focuses on transmission and storage limits, it lacks a unified physical framework to quantify the thermodynamic costs of generating information from compressed laws versus retrieving it […]