Latest AI/ML research from ArXiv and Papers with Code
While AI agents demonstrate remarkable capabilities in reasoning and tool use, they remain fundamentally reactive: they compute responses only after explicit user prompts. This par...
We present MobileGym, a browser-hosted, lightweight, fully controllable environment for everyday mobile use, targeting interaction fidelity without replicating proprietary backends...
Audio-visual generation is rapidly advancing from short clips to minute-long content, while existing evaluation protocols remain largely confined to short-form settings. Existing b...
Subject-driven image generation aims to synthesize new images that preserve the identity of the given subject while following textual instructions. Existing approaches often encode...
Despite the emergence of diffusion large language models (D-LLMs) as an alternative to autoregressive large language models (AR-LLMs), safety monitoring for D-LLMs remains largely ...
We introduce NSF-SciFy, a comprehensive dataset of scientific claims and investigation proposals extracted from National Science Foundation award abstracts. While previous scientif...
Recent video super-resolution (VSR) approaches use deep neural networks to enhance low-quality input videos and recover visual detail, with diffusion-based methods in particular sh...
Real-time streaming joint audio-video generation for character animation requires a generator to speak the requested transcript, maintain visual identity across chunks, and run wit...
Transformer-based large language models are increasingly used for long-horizon tasks; however, their attention mechanism scales poorly with context length. To handle this, we study...
Reinforcement Learning has become a standard paradigm for aligning Large Language Models with human intent and task requirements. While Group Relative Policy Optimization offers an...
Generating complete digital twins from videos requires precise camera control, global scene coverage, and strict spatial-temporal consistency constraints that remain challenging fo...
Metaphorical videos are prevalent across various real-world scenarios to convey complex ideas, and understanding them typically requires high-order cognitive capabilities. The lack...
Recent advances in few-step diffusion distillation have enabled efficient image generation, yet aligning these models with human preferences remains challenging. We propose Reward-...
We present a functional form (that we refer to as a Unified Neural Scaling Law (UNSL)) that accurately models and extrapolates the scaling behaviors of deep neural networks as mult...
Prior work establishes that controlled contrastiveness between self-generated responses from large language models, set via reward scores, improves downstream preference tuning in ...
We introduce LLaVA-OneVision-2 (LLaVA-OV-2), the most capable vision-language model in the LLaVA-OneVision series to date, achieving superior performance across a broad range of mu...
Autonomous computer use agents that powered by multimodal large language models (MLLMs) are emerging as capable assistants for completing complex digital workflows. However, real-w...
Reinforcement learning with verifiable rewards (RLVR) has become a core technique for post-training of Large Language Models (LLMs). While policy optimization is driven by all samp...
Long-form image captioning exposes a reward granularity problem in RL: captions are judged as whole sequences, while the important errors occur at the level of individual visual cl...
Large language models for vertical domains are bottlenecked by the scarcity of complex, domain-specific task-oriented dialogues. Existing data acquisition pipelines face a persiste...
As personal agents evolve to handle complex, user-centric tasks, static plain-text chat is rapidly becoming a bottleneck. Generative UI emerges as the necessary new interface layer...
Long-horizon LLM inference turns the key--value (KV) cache into the dominant GPU memory consumer and makes per-token attention increasingly expensive. Many common eviction policies...
Modern robotic policies increasingly rely on action chunking to execute complex tasks in the physical world. While action chunking improves temporal consistency at moderate action ...
Recent video-based world models have made pixel-space environments interactive at the camera level: users can navigate viewpoints while the model generates coherent visual continua...