arXiv:2510.17476v2 Announce Type: replace Abstract: Equitable access to reliable health information is vital when integrating AI into healthcare. Yet, information quality varies across languages, raising concerns…
arXiv:2604.02915v2 Announce Type: replace Abstract: We present GP-4DGS, a novel framework that integrates Gaussian Processes (GPs) into 4D Gaussian Splatting (4DGS) for principled probabilistic modeling of…
arXiv:2607.07209v1 Announce Type: cross Abstract: Modern federated and streaming learning systems often release intermediate models, so privacy must hold for the full trajectory under adaptive interaction.…
arXiv:2607.06626v1 Announce Type: new Abstract: Recent Vision-Language Models capture increasingly complex aspects of human cognition. Here we ask whether this alignment extends to reward valuation, which…
arXiv:2512.20685v3 Announce Type: replace Abstract: Diffusion models have recently emerged as powerful learners for simulation-based inference (SBI), enabling fast and accurate estimation of latent parameters from…
arXiv:2607.07014v1 Announce Type: cross Abstract: We study a random compositional model for the growth of affine regions in deep piecewise-linear networks. The model is generated by…
Generalist robot manipulation policies have advanced rapidly, yet existing benchmarks remain limited in systematically evaluating their capabilities. Many rely on simple, short-horizon, or skill-narrow tasks with…
Mainstream Vision-Language-Action (VLA) models predict actions primarily from the current observation under a Markovian assumption, thus struggling with long-horizon, temporally dependent tasks. Existing memory-augmented VLAs either…
Humans can navigate an unfamiliar city and gradually form a coherent spatial mental map spanning tens of square kilometers. Can AI build spatial representations at a…
We present LingBot-World 2.0 (also known as LingBot-World-Infinity), an advanced iteration of LingBot-World featuring four distinct upgrades. (1) Our model achieves an unbounded interaction horizon while…
Despite the recent promise in robot control, video generative models suffer from a domain mismatch due to their primary focus on content creation. For example, their…
JD.com, one of the world's largest e-commerce platforms, serves over 700 million active users and millions of merchants, with a catalog of tens of billions of…
Modern one-step diffusion models achieve impressive quality through distribution-based timestep distillation. Yet, they rely on a critical assumption: Teacher and Student must inhabit the same latent…
Reinforcement learning (RL) for non-verifiable instruction following increasingly relies on LLM judges with prompt-specific rubrics as reward signals. While recent methods adapt these rubrics to the…
Reinforcement learning (RL) has become a central component of post-training large language models (LLMs), yet little is understood about how RL adaptation is distributed across transformer…
Large Audio-Language Models (LALMs) are increasingly integrated into daily applications, yet their generative biases remain underexplored. Existing speech fairness benchmarks rely on synthetic speech and Multiple-Choice…
Geometry-conditioned 3D scene generation enables the creation of 3D environments from user-provided geometry, offering direct control over scene structure and object layout. To generate such 3D…
We present RuleChef, a framework that uses large language models (LLMs) to generate executable rules for NLP tasks such as text classification, Named Entity Recognition (NER),…
Multimodal large language models (MLLMs) generate responses autoregressively, integrating visual and linguistic information in an evolving context. Prior work on interpretability has focused on individual layers…
Coding agents increasingly generate pull requests (PRs) for real-world software issues, yet one-shot PR generation remains open-loop: the PR is proposed without systematic review, diagnosis, or…
We introduce Rank-Then-Act (RTA), a framework for learning control policies from expert video demonstrations without environment rewards. RTA trains a Vision-Language Model (VLM) offline as a…
Recently, Joint Embedding Predictive Architectures (JEPAs) have attracted significant attention in the computer vision and machine learning communities as a promising framework for self-supervised representation learning.…
We present HunyuanOCR-1.5, a lightweight end-to-end OCR-specialized vision-language model. HunyuanOCR unifies document parsing, text spotting, information extraction, text-image translation, and multi-image document understanding within a single…
Every chemical language model reading SMILES begins with a tokenizer, yet the field has inherited byte-pair encoding (BPE) from natural language with little scrutiny. In natural…