Related papers: MUSE: A Multi-agent Framework for Unconstrained St…
Large Language Models have demonstrated remarkable capabilities across diverse domains, yet significant challenges persist when deploying them as AI agents for real-world long-horizon tasks. Existing LLM agents suffer from a critical…
User simulators are essential for the scalable training and evaluation of interactive AI systems. However, existing approaches often rely on shallow user profiling, struggle to maintain persona consistency over long interactions, and are…
Despite recent advances, long-sequence video generation frameworks still suffer from significant limitations: poor assistive capability, suboptimal visual quality, and limited expressiveness. To mitigate these limitations, we propose MAViS,…
Transformer-based language model approaches to automated story generation currently provide state-of-the-art results. However, they still suffer from plot incoherence when generating narratives over time, and critically lack basic…
Lifelong user interest modeling is crucial for industrial recommender systems, yet existing approaches rely predominantly on ID-based features, suffering from poor generalization on long-tail items and limited semantic expressiveness. While…
Despite advances in text and visual generation, creating coherent long-form audio narratives remains challenging. Existing frameworks often exhibit limitations such as mismatched character settings with voice performance, insufficient…
Developing AI agents powered by large language models (LLMs) faces significant challenges in achieving true Turing completeness and adaptive, code-driven evolution. Current approaches often generate code independently of its runtime…
Despite recent advancements in text-to-image generation, most existing methods struggle to create images with multiple objects and complex spatial relationships in the 3D world. To tackle this limitation, we introduce a generic AI system,…
Existing text-to-image diffusion models have demonstrated remarkable capabilities in generating high-quality images guided by textual prompts. However, achieving multi-subject compositional synthesis with precise spatial control remains a…
Real-world multimodal applications often require any-to-any capabilities, enabling both understanding and generation across modalities including text, image, audio, and video. However, integrating the strengths of autoregressive language…
There has been a recent explosion of impressive generative models that can produce high quality images (or videos) conditioned on text descriptions. However, all such approaches rely on conditional sentences that contain unambiguous…
This paper proposes to address the word sense ambiguity issue in an unsupervised manner, where word sense representations are learned along a word sense selection mechanism given contexts. Prior work focused on designing a single model to…
Full-stack multimodal interaction in real-time is a central goal in building intelligent embodied agents capable of natural, dynamic communication. However, existing systems are either limited to unimodal generation or suffer from degraded…
While existing text-to-speech (TTS) models exhibit high expressiveness, fine-grained control over composite instructions remains challenging due to the structural mismatch between discrete textual intents and continuous acoustic…
Visual storytelling aims to generate a narrative paragraph from a sequence of images automatically. Existing approaches construct text description independently for each image and roughly concatenate them as a story, which leads to the…
Benchmarks are paramount for gauging progress in the domain of Mobile GUI Agents. In practical scenarios, users frequently fail to articulate precise directives containing full task details at the onset, and their expressions are typically…
Current video generation techniques excel at single-shot clips but struggle to produce narrative multi-shot videos, which require flexible shot arrangement, coherent narrative, and controllability beyond text prompts. To tackle these…
Despite rapid advancements in video generation models, generating coherent storytelling videos that span multiple scenes and characters remains challenging. Current methods often rigidly convert pre-generated keyframes into fixed-length…
In sequence to sequence learning, the self-attention mechanism proves to be highly effective, and achieves significant improvements in many tasks. However, the self-attention mechanism is not without its own flaws. Although self-attention…
Multimodal creative assistants decompose user goals and route tasks to subagents for layout, styling, retrieval, and generation. Retrieval quality is pivotal, yet failures can arise at several stages: understanding user intent, choosing…