Latest AI/ML research from ArXiv and Papers with Code
Parametric retrieval enables LLMs to retrieve tools implicitly by assigning each API a unique virtual token and training the model to generate it via constrained beam search. Tools...
While recent LLM-based terminal agents have demonstrated promising capabilities, the scarcity of high-quality, executable training data remains a critical bottleneck. Existing synt...
Phones are becoming an important execution surface for general-purpose agents, but training open models for reliable phone use remains difficult because the environment that matter...
Long agent traces composed of chains of thought and tool calls accumulate stale content that anchor subsequent generations, and eventually outgrow the context window. Existing scaf...
Video diffusion models have enabled remarkable progress in video generation and editing. However, content preservation remains a core challenge: existing methods regenerate every p...
Multi-view 3D Visual Question Answering (MV3D-VQA) requires integrating partial observations into a coherent 3D scene representation and selecting informative viewpoints for multi-...
Recent attempts to combine large language models (LLMs) with causal discovery ask models to infer pairwise directions, propose graph structures, or inject language-model outputs as...
Enterprise agents increasingly operate inside workspaces: they read heterogeneous files, invoke tools, and deliver business artifacts. We introduce EnterpriseClawBench, an enterpri...
Flow matching has recently emerged as a strong paradigm for state-of-the-art text-to-image (T2I) generation, enabling high-quality generation with a small number of sampling steps....
Computer-use agents (CUAs) now act on a user's behalf across personal applications such as email, calendars, and to-do lists. This cross-application access is useful, but it also c...
Computer-use agents can execute software tasks through either graphical interfaces or programmatic command interfaces, but existing evaluations confound interaction modality with d...
ABACUS is a unified vision-language model that handles object counting, crowd counting, referring-expression counting, and count-faithful image generation without any benchmark-spe...
Training Latent Diffusion Models (LDMs) within Federated Learning (FL) has attracted increasing attention due to its ability to combine the powerful generative capacity of LDMs wit...
Terminal-using agents have quickly become the most popular downstream application of language models (LMs). Despite their prevalence, relatively little academic work has examined R...
Vision Transformers (ViT) dominate computer vision. However, their reliance on rigid patch projectors hinders transfer to Earth Observation (EO), where input modalities, scales, an...
Modern language models, including transformer, recurrent, and memory-based variants, share a common chassis: a stack of identical layers in which parameters are allocated uniformly...
Recently, end-to-end OCR models, exemplified by DeepSeek OCR, have once again thrust OCR into the spotlight. A widely held view is that employing a large language model (LLM) as th...
Chain-of-Thought (CoT) has become a standard method for improving reasoning capabilities in large language models (LLMs) by eliciting step-by-step thinking, but its effectiveness i...
Speech language models (SLMs) have been extensively studied, with the common paradigm incorporating text data and pre-trained text LMs. A leading approach is speech-text interleavi...
Steerability is a defining capability of generalist robot policies, yet remains largely absent in dexterous-hand systems for lack of large-scale, language-aligned, and action-accur...
LLM agents increasingly operate in large tool ecosystems, where real-world tasks require discovering relevant tools, inferring implicit sub-goals, and adapting to dynamic environme...
Generative music systems can now produce impressive audio from text prompts, but audio outputs are difficult to inspect, edit, and diagnose as musical structure. We introduce Libre...
Vision-Language-Action (VLA) models provide a unified paradigm for robotic manipulation, yet their real-world deployment is often bottlenecked by execution efficiency. While existi...
Artificial intelligence systems are commonly evaluated through task performance and behavioral imitation, but such evaluations leave open whether an artificial agent can acquire, s...