Related papers: Multi-CoLoR: Context-Aware Localization and Reason…

Composed Image Retrieval (CIR), which aims to find a target image from a reference image and a modification text, presents the core challenge of performing unified reasoning across visual and semantic modalities. While current approaches…

Localizing text instances in natural scenes is regarded as a fundamental challenge in computer vision. Nevertheless, owing to the extremely varied aspect ratios and scales of text instances in real scenes, most conventional text detectors…

In modern software development, developers frequently need to understand code behavior at a glance -- whether reviewing pull requests, debugging issues, or navigating unfamiliar codebases. This ability to reason about dynamic program…

The performance of repository-level code completion depends upon the effective leverage of both general and repository-specific knowledge. Despite the impressive capability of code LLMs in general code completion tasks, they often exhibit…

Large Language Models (LLMs) have shown promise in automating code generation and software engineering tasks, yet they often struggle with complex, multi-file projects due to context limitations and knowledge gaps. We propose a novel…

Multimodal large language models often struggle with faithful reasoning in complex visual scenes, where intricate entities and relations require precise visual grounding at each step. This reasoning unfaithfulness frequently manifests as…

Despite the substantial success of Information Retrieval (IR) in various NLP tasks, most IR systems predominantly handle queries and corpora in natural language, neglecting the domain of code retrieval. Code retrieval is critically…

Large Language Models (LLMs) have achieved remarkable success in source code understanding, yet as software systems grow in scale, computational efficiency has become a critical bottleneck. Currently, these models rely on a text-based…

Recent research has explored the use of Large Language Models (LLMs) for tackling complex graph reasoning tasks. However, due to the intricacies of graph structures and the inherent limitations of LLMs in handling long text, current…

As large language models (LLMs) are applied to increasingly longer and more complex tasks, there is a growing need for realistic long-context benchmarks that require selective reading and integration of heterogeneous, multi-modal…

Contextual Partitioning introduces an innovative approach to enhancing the architectural design of large-scale computational models through the dynamic segmentation of parameters into context-aware regions. This methodology emphasizes the…

While large language models (LLMs) exhibit strong multilingual abilities, their reliance on English as latent representations creates a translation barrier, where reasoning implicitly depends on internal translation into English. When this…

Optimizing the trade-off among predictive performance and computational cost is a central focus in the deployment of Large Language Models (LLMs). Current routing methods primarily rely on direct mapping from queries to models based on…

Understanding an unfamiliar codebase is an essential task for developers in various scenarios, such as during the onboarding process. Especially when the codebase is large and time is limited, achieving a decent level of comprehension…

Large language models (LLMs) have achieved strong performance in code generation, but most methods rely on autoregressive decoding without global planning, often leading to locally coherent yet globally suboptimal solutions (e.g., failing…

Multi-encoder models are a broad family of context-aware neural machine translation systems that aim to improve translation quality by encoding document-level contextual information alongside the current sentence. The context encoding is…

Code search, framed as information retrieval (IR), underpins modern software engineering and increasingly powers retrieval-augmented generation (RAG), improving code discovery, reuse, and the reliability of LLM-based coding. Yet existing…

Chain-of-Thought (CoT) reasoning has been widely adopted to enhance Large Language Models (LLMs) by decomposing complex tasks into simpler, sequential subtasks. However, extending CoT to vision-language reasoning tasks remains challenging,…

Multi-label recognition with partial labels (MLR-PL), in which only some labels are known while others are unknown for each image, is a practical task in computer vision, since collecting large-scale and complete multi-label datasets is…

Recent advancements in Large Language Models (LLMs) have transformed code generation from natural language queries. However, despite their extensive knowledge and ability to produce high-quality code, LLMs often struggle with contextual…