Related papers: EFACT: an External Function Auto-Completion Tool t…
We present a novel bottom-up method for the synthesis of functional recursive programs. While bottom-up synthesis techniques can work better than top-down methods in certain settings, there is no prior technique for synthesizing recursive…
Tree-based speculative decoding accelerates autoregressive generation by verifying multiple draft candidates in parallel, but this advantage weakens for sparse Mixture-of-Experts (MoE) models. As the draft tree grows, different branches…
Task decomposition is a fundamental mechanism in program synthesis, enabling complex problems to be broken down into manageable subtasks. ExeDec, a state-of-the-art program synthesis framework, employs this approach by combining a Subgoal…
Local feature matching is an essential technique in image matching and plays a critical role in a wide range of vision-based applications. However, existing Transformer-based detector-free local feature matching methods encounter challenges…
Detecting semantically similar functions -- a crucial analysis capability with broad real-world security usages including vulnerability detection, malware lineage, and forensics -- requires understanding function behaviors and intentions.…
Effect handlers have been gathering momentum as a mechanism for modular programming with user-defined effects. Effect handlers allow for non-local control flow mechanisms such as generators, async/await, lightweight threads and coroutines…
Despite strong performance in many sequence-to-sequence tasks, autoregressive models trained with maximum likelihood estimation suffer from exposure bias, i.e. the discrepancy between the ground-truth prefixes used during training and the…
Recently, the explicit constraint force method (ECFM) was introduced as a principled approach to solution reconstruction in the presence of missing physics. In solution reconstruction, parameters of a physical model are estimated from…
Basic Linear Algebra Subprograms (BLAS) is a core library in scientific computing and machine learning. This paper presents FT-BLAS, a new implementation of BLAS routines that not only tolerates soft errors on the fly, but also provides…
Decompilation is foundational to binary analysis, yet conventional tools prioritize human readability over strict recompilability and verifiable runtime correctness. While recent LLM-based approaches attempt to refine decompiled pseudocode,…
To reduce the source of potential exploits, binary debloating or specialization tools are used to remove unnecessary code from binaries. This paper presents a new binary debloating and specialization tool, LeanBin, that harnesses lifting…
Exemplar-Free Class-Incremental Learning (EFCIL) aims to sequentially learn from distinct categories without retaining exemplars but easily suffers from catastrophic forgetting of learned knowledge. While existing EFCIL methods leverage…
Recent years has witnessed dramatic progress of neural machine translation (NMT), however, the method of manually guiding the translation procedure remains to be better explored. Previous works proposed to handle such problem through…
A statistical emulator can be used as a surrogate of complex physics-based calculations to drastically reduce the computational cost. Its successful implementation hinges on an accurate representation of the nonlinear response surface with…
Accurate electromagnetic (EM) feature extraction, including element characterization, eigenmodes, and field distributions, is essential for superconducting quantum circuit design. To streamline this process, we present a workflow built…
This paper introduces EXaCTz, a parallel algorithm that concurrently preserves extremum graphs and contour trees in lossy-compressed scalar field data. While error-bounded lossy compression is essential for large-scale scientific…
Multimodal retrieval still leans on embedding-based models like CLIP for fast vector search over pre-computed image embeddings. Yet, unlike text retrieval, where joint-encoder rerankers are standard, comparable vision-language rerankers are…
Automating the formalization of mathematical statements for theorem proving remains a major challenge for Large Language Models (LLMs). LLMs struggle to identify and utilize the prerequisite mathematical knowledge and its corresponding…
Training a referring expression comprehension (ReC) model for a new visual domain requires collecting referring expressions, and potentially corresponding bounding boxes, for images in the domain. While large-scale pre-trained models are…
This paper introduces innovative frameworks for visual abstract reasoning, aiming to boost deep learning model performance. It emphasizes the importance of separating abstract concept and reasoning feature extraction processes. The…