Related papers: Closing the Loop: Universal Repository Representat…
Knowledge graphs (KGs) capture knowledge in the form of head--relation--tail triples and are a crucial component in many AI systems. There are two important reasoning tasks on KGs: (1) single-hop knowledge graph completion, which involves…
Photonic Reservoir Computing (RC) systems leverage the complex propagation and nonlinear interaction of optical waves to perform information processing tasks. These systems employ a combination of optical data encoding (in the field…
Optimizing the performance of large-scale software repositories demands expertise in code reasoning and software engineering (SWE) to reduce runtime while preserving program correctness. However, most benchmarks emphasize what to fix rather…
Rapid advances in GPU hardware and multiple areas of Deep Learning open up a new opportunity for billion-scale information retrieval with exhaustive search. Building on top of the powerful concept of semantic learning, this paper proposes a…
Repository-level coding agents must first localize the files and symbols relevant to a task; failures at this stage can cascade across downstream objectives ranging from patch generation to test writing and codebase question answering.…
Large language models (LLMs) have exhibited remarkable few-shot learning capabilities and unified the paradigm of NLP tasks through the in-context learning (ICL) technique. Despite the success of ICL, the quality of the exemplar…
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…
Code generation is crucial in software engineering for automating the coding process efficiently. While test-time computation methods show promise, they suffer from high latency due to multiple computation rounds. To overcome this, we…
Many research groups aspire to make data and code FAIR and reproducible, yet struggle because the data and code life cycles are disconnected, executable environments are often missing from published work, and technical skill requirements…
Universal image restoration (UIR) aims to recover clean images from diverse and unknown degradations using a unified model. Existing UIR methods primarily focus on pixel reconstruction and often lack explicit diagnostic reasoning over…
Interpreting the reasoning process from questions to answers poses a challenge in approaching explainable QA. A recently proposed structured reasoning format, entailment tree, manages to offer explicit logical deductions with entailment…
Large language models (LLMs) have recently shown strong progress on scientific reasoning, yet two major bottlenecks remain. First, explicit retrieval fragments reasoning, imposing a hidden "tool tax" of extra tokens and steps. Second,…
We present a repository decomposition system that converts large software repositories into a vectorized knowledge graph which mirrors project architectural and semantic structure, capturing semantic relationships and allowing a significant…
In this paper, we propose Robo-SGG, a plug-and-play module for robust scene graph generation (SGG). Unlike standard SGG, the robust scene graph generation aims to perform inference on a diverse range of corrupted images, with the core…
Generative Recommendation (GR) has become a promising paradigm for large-scale recommendation systems. However, existing GR models typically perform single-pass decoding without explicit refinement, causing early deviations to accumulate…
We propose a new class of efficient decoding algorithms for Reed-Muller (RM) codes over binary-input memoryless channels. The algorithms are based on projecting the code on its cosets, recursively decoding the projected codes (which are…
Analyzing programs with loops is a challenging task, suffering from potential issues such as indeterminate number of iterations and exponential growth of control flow complexity. Loop summarization, as a static analysis method for concrete…
This manuscript explores the evolutionary emergence of semantic closure -- the self-referential mechanism through which symbols actively construct and interpret their own functional contexts -- by integrating concepts from relational…
Single image super resolution (SR) has seen major performance leaps in recent years. However, existing methods do not allow exploring the infinitely many plausible reconstructions that might have given rise to the observed low-resolution…
In this paper, we investigate code-integrated reasoning, where models generate code when necessary and integrate feedback by executing it through a code interpreter. To acquire this capability, models must learn when and how to use external…