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

Visual grounding is a ubiquitous building block in many vision-language tasks and yet remains challenging due to large variations in visual and linguistic features of grounding entities, strong context effect and the resulting semantic…

Despite significant progress, large language models (LLMs) still struggle with long contexts due to memory limitations and their inability to tackle complex and long-context tasks. Additionally, LLMs often suffer from a lack of transparency…

Source code summaries are short natural language descriptions of code snippets that help developers better understand and maintain source code. There has been a surge of work on automatic code summarization to reduce the burden of writing…

Separation logic is often praised for its ability to closely mimic the locality of state updates when reasoning about them at the level of assertions. The prover only needs to concern themselves with the footprint of the computation at…

Recovering the structure of causal graphical models from observational data is an essential yet challenging task for causal discovery in scientific scenarios. Domain-specific causal discovery usually relies on expert validation or prior…

Cross-lingual cross-modal retrieval (CCR) aims to retrieve visually relevant content based on non-English queries, without relying on human-labeled cross-modal data pairs during training. One popular approach involves utilizing machine…

Multimodal Large Language Models (MLLMs) are increasingly deployed in real-world applications, yet their ability to make context-aware safety decisions remains limited. Existing methods often fail to balance oversensitivity (unjustified…

Solving multi-label recognition (MLR) for images in the low-label regime is a challenging task with many real-world applications. Recent work learns an alignment between textual and visual spaces to compensate for insufficient image labels,…

The progress made in code modeling has been tremendous in recent years thanks to the design of natural language processing learning approaches based on state-of-the-art model architectures. Nevertheless, we believe that the current…

Reasoning about images/objects and their hierarchical interactions is a key concept for the next generation of computer vision approaches. Here we present a new framework to deal with it through a visual hierarchical context-based…

With the advent of large language models(LLMs) enhanced by the chain-of-thought(CoT) methodology, visual reasoning problem is usually decomposed into manageable sub-tasks and tackled sequentially with various external tools. However, such a…

Many of the existing approaches for program comprehension rely on the linguistic information found in source code, such as identifier names and comments. Semantic clustering is one such technique for modularization of the system that relies…

We introduce LOCORE, Long-Context Re-ranker, a model that takes as input local descriptors corresponding to an image query and a list of gallery images and outputs similarity scores between the query and each gallery image. This model is…

Recent advances in large language models (LLMs), particularly those enhanced through reinforced post-training, have demonstrated impressive reasoning capabilities, as exemplified by models such as OpenAI o1 and DeepSeek-R1. However, these…

Large language models (LLMs) have recently enabled coding agents capable of generating, executing, and revising visualization code. However, existing models often fail in practical workflows due to limited language coverage, unreliable…

Multimodal large language models (MLLMs) have streamlined front-end interface development by automating code generation. However, these models also introduce challenges in ensuring code quality. Existing approaches struggle to maintain both…

Recent advancements in code-fluent Large Language Models (LLMs) enabled the research on repository-level code editing. In such tasks, the model navigates and modifies the entire codebase of a project according to request. Hence, such tasks…

Conditional layout generation aims to automatically generate visually appealing and semantically coherent layouts from user-defined constraints. While recent methods based on generative models have shown promising results, they typically…

In context learning (ICL) underpins recent advances in large language models (LLMs), although its role and performance in causal reasoning remains unclear. Causal reasoning demands multihop composition and strict conjunctive control, and…

Repository-level code generation aims to generate code within the context of a specified repository. Existing approaches typically employ retrieval-augmented generation (RAG) techniques to provide LLMs with relevant contextual information…