Developing robust world model reasoning is crucial for large language model (LLM) agents to plan and interact in complex environments. While multi-turn interact...
Recently, multi-person video generation has started to gain prominence. While a few preliminary works have explored audio-driven multi-person talking video gene...
Recent advances in large language models (LLMs) have enabled breakthroughs in mathematical discovery, exemplified by AlphaEvolve, a closed-source system that ev...
Large Vision Language Models (VLMs) effectively bridge the modality gap through extensive pretraining, acquiring sophisticated visual representations aligned wi...
Current world models lack a unified and controlled setting for systematic evaluation, making it difficult to assess whether they truly capture the underlying ru...
Language models have seen enormous progress on advanced benchmarks in recent years, but much of this progress has only been possible by using more costly models...
Deep learning approaches to object detection have achieved reliable detection of specific object classes in images. However, extending a model's detection capab...
Inverse heat problems refer to the estimation of material thermophysical properties given observed or known heat diffusion behaviour. Inverse heat problems have...
This paper studies the role of activation functions in learning modular addition with two-layer neural networks. We first establish a sharp expressivity gap: si...
Offline reinforcement learning (RL) enables agents to learn optimal policies from pre-collected datasets. However, datasets containing suboptimal and fragmented...
Machine learning models perform well across domains such as diagnostics, weather forecasting, NLP, and autonomous driving, but their limited uncertainty handlin...
We introduce SuperIntelliAgent, an agentic learning framework that couples a trainable small diffusion model (the learner) with a frozen large language model (t...
Recent advances in generative world models have enabled remarkable progress in creating open-ended game environments, evolving from static scene synthesis towar...
Recent advances in text-to-video (T2V) and image-to-video (I2V) models, have enabled the creation of visually compelling and dynamic videos from simple textual ...
Automated vulnerability patching is crucial for software security, and recent advancements in Large Language Models (LLMs) present promising capabilities for au...
Underwater object tracking is challenging due to wavelength dependent attenuation and scattering, which severely distort appearance across depths and water cond...
We present LFM2, a family of Liquid Foundation Models designed for efficient on-device deployment and strong task capabilities. Using hardware-in-the-loop archi...
Split learning is well known as a method for resolving data privacy concerns by training a model on distributed devices, thereby avoiding data sharing that rais...
Small and medium-sized enterprises (SMEs) in Iran increasingly leverage Telegram for sales, where real-time engagement is essential for conversion. However, dev...
Direct Preference Optimization (DPO) is a widely used reinforcement learning from human feedback (RLHF) method across various domains. Recent research has incre...
We study the online unweighted bipartite matching problem in the random arrival order model, with $n$ offline and $n$ online vertices, in the learning-augmented...
We present the Hierarchical AI-Meteorologist, an LLM-agent system that generates explainable weather reports using a hierarchical forecast reasoning and weather...
Unifying multimodal understanding, generation and reconstruction representation in a single tokenizer remains a key challenge in building unified models. Previo...
Novice and expert users have different systematic preferences in task-oriented dialogues. However, whether catering to these preferences actually improves user ...
