Related papers: Proactive Memory for Ad-Hoc Recall over Streaming …

Recent progress in video large language models (Video-LLMs) has enabled strong offline reasoning over long and complex videos. However, real-world deployments increasingly require streaming perception and proactive interaction, where video…

Diffusion language models (DLMs) promise parallel, order-agnostic generation, but on standard benchmarks they have historically lagged behind autoregressive models in sample quality and diversity. Recent continuous flow and diffusion…

Streaming video models should respond the moment an event unfolds, not after the moment has passed. Yet existing online VideoQA benchmarks remain largely retrospective. They pause the video at fixed timestamps, pose questions about current…

Online lifelong learning enables agents to accumulate experience across interactions and continually improve on long-horizon tasks. However, existing methods typically treat retrieval from past experience as a passive operation, triggering…

Standard Large Language Models (LLMs) struggle with handling dialogues with long contexts due to efficiency and consistency issues. According to our observation, dialogue contexts are highly structured, and the special token of…

Sequential memory, the ability to form and accurately recall a sequence of events or stimuli in the correct order, is a fundamental prerequisite for biological and artificial intelligence as it underpins numerous cognitive functions (e.g.,…

Long-horizon dialogue systems suffer from semanticdrift and unstable memory retention across extended sessions. This paper presents a Multi-Layer Memory Framework that decomposes dialogue history into working, episodic, and semantic layers…

Long-term memory (LTM) is essential for large language models (LLMs) to achieve autonomous intelligence in complex, evolving environments. Despite increasing efforts in memory-augmented and retrieval-based architectures, there remains a…

Long-sequence streaming 3D reconstruction remains a significant open challenge. Existing autoregressive models often fail when processing long sequences because they anchor poses to the first frame, leading to attention decay, scale drift,…

Despite recent advances in understanding and leveraging long-range conversational memory, existing benchmarks still lack systematic evaluation of large language models(LLMs) across diverse memory dimensions, particularly in multi-session…

Incorporating speech understanding capabilities into pretrained large-language models has become a vital research direction (SpeechLLM). The previous architectures can be categorized as: i) GPT-style, prepend speech prompts to the text…

Deploying large language model (LLM)-driven conversational agents in enterprise settings requires prompts that are simultaneously correct at launch and resilient to the non-deterministic behavioral drift that characterizes production LLM…

Despite advancements in Video Large Language Models (Vid-LLMs) improving multimodal understanding, challenges persist in streaming video reasoning due to its reliance on contextual information. Existing paradigms feed all available…

World simulation has gained increasing popularity due to its ability to model virtual environments and predict the consequences of actions. However, the limited temporal context window often leads to failures in maintaining long-term…

Real-time speech synthesis requires balancing inference latency and acoustic fidelity for interactive applications. Conventional continuous text-to-speech pipelines require computationally intensive neural vocoders to reconstruct phase…

Real-time LLM interactions demand streamed token generations, where text tokens are progressively generated and delivered to users while balancing two objectives: responsiveness (i.e., low time-to-first-token) and steady generation…

Statefulness is essential for large language model (LLM) agents to perform long-term planning and problem-solving. This makes memory a critical component, yet its management and evolution remain largely underexplored. Existing evaluations…

Vision-and-Language Navigation (VLN) in real-world settings requires agents to process continuous visual streams and generate actions with low latency grounded in language instructions. While Video-based Large Language Models (Video-LLMs)…

Despite rapid progress in Multi-modal Large Language Models and Large Audio-Language Models, existing audio benchmarks largely test semantics that can be recovered from text captions, masking deficits in fine-grained perceptual reasoning.…

We introduce ProVideLLM, an end-to-end framework for real-time procedural video understanding. ProVideLLM integrates a multimodal cache configured to store two types of tokens - verbalized text tokens, which provide compressed textual…