Related papers: LMEB: Long-horizon Memory Embedding Benchmark

Long-term agent memory is increasingly multimodal, yet existing evaluations rarely test whether agents preserve the visual evidence needed for later reasoning. In prior work, many visually grounded questions can be answered using only…

Long-term memory systems enable conversational agents based on large language models (LLMs) to retain, retrieve, and apply user-specific information across multi-session interactions. However, existing evaluations mainly assess…

We introduce llama-embed-nemotron-8b, an open-weights text embedding model that achieves state-of-the-art performance on the Multilingual Massive Text Embedding Benchmark (MMTEB) leaderboard as of October 21, 2025. While recent models show…

Cross-modal video-text retrieval, a challenging task in the field of vision and language, aims at retrieving corresponding instance giving sample from either modality. Existing approaches for this task all focus on how to design encoding…

Large language models (LLMs) acquire knowledge across diverse domains such as science, history, and geography encountered during generative pre-training. However, due to their stochasticity, it is difficult to predict what LLMs have…

Long-term memory is critical for dialogue systems that support continuous, sustainable, and personalized interactions. However, existing methods rely on continuous summarization or OpenIE-based graph construction paired with fixed…

MLLMs have been successfully applied to multimodal embedding tasks, yet their generative reasoning capabilities remain underutilized. Directly incorporating chain-of-thought reasoning into embedding learning introduces two fundamental…

Universal multimodal retrieval (UMR), which aims to address complex retrieval tasks where both queries and candidates span diverse modalities, has been significantly advanced by the emergence of MLLMs. While state-of-the-art MLLM-based…

Transformer-based large language models (LLMs) have achieved remarkable success, yet their standard attention mechanism incurs quadratic computation and memory costs with respect to sequence length, posing a major bottleneck for…

Recent studies have adapted generative Multimodal Large Language Models (MLLMs) into embedding extractors for vision tasks, typically through fine-tuning to produce universal representations. However, their performance on video remains…

We introduce EMemBench, a programmatic benchmark for evaluating long-term memory of agents through interactive games. Rather than using a fixed set of questions, EMemBench generates questions from each agent's own trajectory, covering both…

Current evaluations of long-term memory in LLMs are fundamentally static. By fixating on simple retrieval and short-context inference, they neglect the multifaceted nature of complex memory systems, such as dynamic state tracking and…

Since real-world objects and their interactions are often multi-modal and multi-typed, heterogeneous networks have been widely used as a more powerful, realistic, and generic superclass of traditional homogeneous networks (graphs).…

Multimodal large language models (MLLMs) have achieved remarkable success in vision-language tasks, but their reliance on vast, internet-sourced data raises significant privacy and security concerns. Machine unlearning (MU) has emerged as a…

Text embedding models serve as a fundamental component in real-world search applications. By mapping queries and documents into a shared embedding space, they deliver competitive retrieval performance with high efficiency. However, their…

Continual learning has become essential in many practical applications such as online news summaries and product classification. The primary challenge is known as catastrophic forgetting, a phenomenon where a model inadvertently discards…

Embedding models play a crucial role in Natural Language Processing (NLP) by creating text embeddings used in various tasks such as information retrieval and assessing semantic text similarity. This paper focuses on research related to…

Robust unlearning is crucial for safely deploying large language models (LLMs) in environments where data privacy, model safety, and regulatory compliance must be ensured. Yet the task is inherently challenging, partly due to difficulties…

Multimodal retrieval is becoming a crucial component of modern AI applications, yet its evaluation lags behind the demands of more realistic and challenging scenarios. Existing benchmarks primarily probe surface-level semantic…

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…