Related papers: S3Mem: Structured Spatiotemporal Scene-Event Memor…

Visual-spatial understanding, the ability to infer object relationships and layouts from visual input, is fundamental to downstream tasks such as robotic navigation and embodied interaction. However, existing methods face spatial…

Memory is a central capability for LLM agents operating across long-horizon tasks. Existing memory benchmarks predominantly evaluate retention of personalized information in multi-turn chat scenarios, overlooking the dynamic memory…

Retrieval-Augmented Generation (RAG) grounds language models in external evidence, but multi-hop question answering remains difficult because iterative pipelines must control what to retrieve next and when the available evidence is…

We propose a novel memory module for building video generators capable of interactively exploring environments. Previous approaches have achieved similar results either by out-painting 2D views of a scene while incrementally reconstructing…

Large Language Models (LLMs) falter in multi-step interactions -- often hallucinating, repeating actions, or misinterpreting user corrections -- due to reliance on linear, unstructured context. This fragility stems from the lack of…

In the rapidly evolving domain of video understanding, Video Question Answering (VideoQA) remains a focal point. However, existing datasets exhibit gaps in temporal and spatial granularity, which consequently limits the capabilities of…

Although Transformers with fully connected self-attentions are powerful to model long-term dependencies, they are struggling to scale to long texts with thousands of words in language modeling. One of the solutions is to equip the model…

Large language models (LLMs) substantially enhance developer productivity in repository-level code generation through interactive collaboration. However, as interactions progress, repository context must be continuously preserved and…

Understanding long-context visual information remains a fundamental challenge for vision-language models, particularly in agentic tasks such as GUI control and web navigation. While web pages and GUI environments are inherently structured…

Real-world agents operate over long and evolving horizons, where information is repeatedly updated and may interfere across memories, requiring accurate recall and aggregated reasoning over multiple pieces of information. However, existing…

Multimodal document question answering requires retrieving dispersed evidence from visually rich long documents and performing reliable reasoning over heterogeneous information. Existing multimodal RAG systems remain limited by two…

Memory systems have been designed to leverage past experiences in Large Language Model (LLM) agents. However, many deployed memory systems primarily optimize compression and storage, with comparatively less emphasis on explicit, closed-loop…

Navigating and understanding complex environments over extended periods of time is a significant challenge for robots. People interacting with the robot may want to ask questions like where something happened, when it occurred, or how long…

Despite the remarkable success of Vision-Language Models (VLMs), their performance on a range of complex visual tasks is often hindered by a "visual processing bottleneck": a propensity to lose grounding in visual evidence and exhibit a…

Multi-step retrieval-augmented generation (RAG) has become a widely adopted strategy for enhancing large language models (LLMs) on tasks that demand global comprehension and intensive reasoning. Although many RAG systems incorporate a…

Long-horizon language agents accumulate conversation history far faster than any fixed context window can hold, making memory management critical to both answer accuracy and serving cost. Existing approaches either expand the context window…

Large language models (LLMs) are largely static and often redo reasoning or repeat mistakes. Prior experience reuse typically relies on external retrieval, which is similarity-based, can introduce noise, and adds latency. We introduce SEAM…

Autoregressive video diffusion models enable open-ended generation through local attention and KV caching. However, existing training-free long-video optimization methods mainly focus on stable extension under a single prompt, making them…

Although LLM agents can leverage tools for complex tasks, they still need memory to maintain cross-turn consistency and accumulate reusable information in long-horizon interactions. However, retrieval-based external memory systems incur low…

While large language models (LLMs) have made notable advancements in natural language processing, they continue to struggle with processing extensive text. Memory mechanism offers a flexible solution for managing long contexts, utilizing…