相关论文: CogCanvas: Verbatim-Grounded Artifact Extraction f…

Large vision-language models (VLMs) have advanced multimodal tasks such as video question answering (QA). However, VLMs face the challenge of selecting frames effectively and efficiently, as standard uniform sampling is expensive and…

We propose an end-to-end, domain-independent neural encoder-aligner-decoder model for selective generation, i.e., the joint task of content selection and surface realization. Our model first encodes a full set of over-determined database…

When video reasoning requires external knowledge, many systems with large multimodal models (LMMs) adopt retrieval augmentation to supply the missing context. Appending textual or multi-clip evidence, however, forces heterogeneous signals…

Understanding abstract meanings is crucial for advanced language comprehension. Despite extensive research, abstract words remain challenging due to their non-concrete, high-level semantics. SemEval-2021 Task 4 (ReCAM) evaluates models'…

Large Vision-Language Models (LVLMs) demonstrate remarkable performance in short-video tasks such as video question answering, but struggle in long-video understanding. The linear frame sampling strategy, conventionally used by LVLMs, fails…

Retrieval-Augmented Generation (RAG) allows overcoming the limited knowledge of LLMs by extending the input with external information. As a consequence, the contextual inputs to the model become much longer which slows down decoding time…

Document-based Question-Answering (QA) tasks are crucial for precise information retrieval. While some existing work focus on evaluating large language models performance on retrieving and answering questions from documents, assessing the…

We introduce VoxRAG, a modular speech-to-speech retrieval-augmented generation system that bypasses transcription to retrieve semantically relevant audio segments directly from spoken queries. VoxRAG employs silence-aware segmentation,…

Large Language Models (LLMs) have demonstrated superior listwise ranking performance. However, their superior performance often relies on large-scale parameters (\eg, GPT-4) and a repetitive sliding window process, which introduces…

Long Context Language Models (LCLMs) have emerged as a new paradigm to perform Information Retrieval (IR), which enables the direct ingestion and retrieval of information by processing an entire corpus in their single context, showcasing…

To deliver coherent and personalized experiences in long-term conversations, existing approaches typically perform retrieval augmented response generation by constructing memory banks from conversation history at either the turn-level,…

This study presents a question-based knowledge encoding approach that improves retrieval-augmented generation (RAG) systems without requiring fine-tuning or traditional chunking. We encode textual content using generated questions that span…

Graph-structured retrieval-augmented generation (RAG) systems can improve answer quality on multi-hop questions, but many current systems rely on large language models (LLMs) to extract entities, relations, and summaries during indexing.…

It is always well believed that modeling relationships between objects would be helpful for representing and eventually describing an image. Nevertheless, there has not been evidence in support of the idea on image description generation.…

Recent advancements in large language models (LLMs) underscore the need for more comprehensive evaluation methods to accurately assess their reasoning capabilities. Existing benchmarks are often domain-specific and thus cannot fully capture…

Contrastively-trained Vision-Language Models (VLMs), such as CLIP, have become the standard approach for learning discriminative vision-language representations. However, these models often exhibit shallow language understanding,…

Modern Large Language Models (LLMs) are increasingly trained to support very large context windows. We present Compactor, a training-free, query-agnostic KV compression strategy that uses approximate leverage scores to determine token…

Augmenting Large Language Models (LLMs) with information retrieval capabilities (i.e., Retrieval-Augmented Generation (RAG)) has proven beneficial for knowledge-intensive tasks. However, understanding users' contextual search intent when…

To support long-term interaction in complex environments, LLM agents require memory systems that manage historical experiences. Existing approaches either retain full interaction histories via passive context extension, leading to…

This paper explores how large language models can leverage multi-level contextual information to predict group coordination patterns in collaborative mixed reality environments. We demonstrate that encoding individual behavioral profiles,…