Related papers: $\text{R}^2\text{R}$: A Route-to-Rerank Post-Train…

Large Language Models (LLMs) perform well in general QA but often struggle in domain-specific scenarios. Retrieval-Augmented Generation (RAG) introduces external knowledge but suffers from hallucinations and latency due to noisy retrievals.…

Grounded Multimodal Named Entity Recognition (GMNER) extends traditional NER by jointly detecting textual mentions and grounding them to visual regions. While existing supervised methods achieve strong performance, they rely on costly…

Chain-of-thought has been proven essential for enhancing the complex reasoning abilities of Large Language Models (LLMs), but it also leads to high computational costs. Recent advances have explored the method to route queries among…

Retrieval Augmented Generation (RAG) has greatly improved the performance of Large Language Model (LLM) responses by grounding generation with context from existing documents. These systems work well when documents are clearly relevant to a…

Visual Place Recognition (VPR) estimates the location of query images by matching them with images in a reference database. Conventional methods generally adopt aggregated CNN features for global retrieval and RANSAC-based geometric…

Accurate 3D lane segment detection and topology reasoning are critical for structured online map construction in autonomous driving. Recent transformer-based approaches formulate this task as query-based set prediction, yet largely inherit…

Retrieval-Augmented Generation (RAG) has become ubiquitous when deploying Large Language Models (LLMs), as it can address typical limitations such as generating hallucinated or outdated information. However, when building real-world RAG…

Unlearning in large foundation models (e.g., LLMs) is essential for enabling dynamic knowledge updates, enforcing data deletion rights, and correcting model behavior. However, existing unlearning methods often require full-model fine-tuning…

Reranker improves retrieval performance by capturing document interactions. At one extreme, graph-aware adaptive retrieval (GAR) represents an information-rich regime, requiring a pre-computed document similarity graph in reranking.…

Vision-centric retrieval for VQA requires retrieving images to supply missing visual cues and integrating them into the reasoning process. However, selecting the right images and integrating them effectively into the model's reasoning…

Auto-encoder is an important architecture to understand point clouds in an encoding and decoding procedure of self reconstruction. Current auto-encoder mainly focuses on the learning of global structure by global shape reconstruction, while…

Most deep reinforcement learning (RL) algorithms distill experience into parametric behavior policies or value functions via gradient updates. While effective, this approach has several disadvantages: (1) it is computationally expensive,…

Large Language Models (LLMs) have shown promising performance on diverse medical benchmarks, highlighting their potential in supporting real-world clinical tasks. Retrieval-Augmented Generation (RAG) has emerged as a key approach for…

Retrieval-Augmented Generation (RAG) mitigates hallucination in LLMs by incorporating external knowledge, but relies on chunk-based retrieval that lacks structural semantics. GraphRAG methods improve RAG by modeling knowledge as…

The data-to-equation (Data2Eqn) task aims to discover interpretable mathematical equations that map observed values to labels, offering physical insights and broad applicability across academic and industrial domains. Genetic programming…

Retrieval-Augmented Generation (RAG) struggles on long, structured financial filings where relevant evidence is sparse and cross-referenced. This paper presents a systematic investigation of advanced metadata-driven Retrieval-Augmented…

Retrieval-Augmented Generation (RAG) enhances the factual grounding of Large Language Models by conditioning their outputs on external documents. However, standard embedding-based retrievers treat naturally structured corpora, such as…

We present the Frontier Aware Search with backTracking (FAST) Navigator, a general framework for action decoding, that achieves state-of-the-art results on the Room-to-Room (R2R) Vision-and-Language navigation challenge of Anderson et. al.…

In large multimodal models (LMMs), the perception of non-language modalities (e.g., visual representations) is usually not on par with the large language models (LLMs)' powerful reasoning capabilities, deterring LMMs' performance on…

Fine-tuning is an immensely resource-intensive process when retraining Large Language Models (LLMs) to incorporate a larger body of knowledge. Although many fine-tuning techniques have been developed to reduce the time and computational…