Related papers: Desyan: A Platform for Seamless Value-Flow and Sym…
When large language models are fine-tuned to generate persona- or tone-conditioned responses, their output diversity is severely limited--a failure we term Cross-Style Collapse. We trace this collapse to the cross-entropy objective, which…
We present Scallop, a language which combines the benefits of deep learning and logical reasoning. Scallop enables users to write a wide range of neurosymbolic applications and train them in a data- and compute-efficient manner. It achieves…
Assertion checking is an invaluable programmer's tool for finding many classes of errors or verifying their absence in dynamic languages such as Prolog. For Prolog programmers this means being able to have relevant properties such as modes,…
Finding image correspondences remains a challenging problem in the presence of intra-class variations and large changes in scene layout.~Semantic flow methods are designed to handle images depicting different instances of the same object or…
Flowcharts are typically presented as images, driving the trend of using vision-language models (VLMs) for end-to-end flowchart understanding. However, two key challenges arise: (i) Limited controllability--users have minimal influence over…
Explicit Chain-of-Thought improves the reasoning performance of large language models but often incurs high inference cost due to verbose token-level traces. While recent approaches reduce this overhead via concise prompting or step…
Despite rapid progress, multimodal reasoning still lacks a systematic approach to synthesize large-scale vision-centric datasets beyond visual math. We introduce a framework able to synthesize vision-centric problems spanning diverse levels…
Flow matching models have recently emerged as an efficient alternative to diffusion, especially for text-guided image generation and editing, offering faster inference through continuous-time dynamics. However, existing flow-based editors…
Symbolic execution now becomes an indispensable technique for software testing and program analysis. There are several symbolic execution tools available off-the-shelf, and we need a practical benchmark approach to learn their capabilities.…
Static analysis tools are frequently used to detect potential vulnerabilities in software systems. However, an inevitable problem of these tools is their large number of warnings with a high false positive rate, which consumes time and…
The verbosity of Chain-of-Thought (CoT) reasoning hinders its mass deployment in efficiency-critical applications. Recently, implicit CoT approaches have emerged, which encode reasoning steps within LLM's hidden embeddings (termed…
Semantic information has been proved effective in scene text recognition. Most existing methods tend to couple both visual and semantic information in an attention-based decoder. As a result, the learning of semantic features is prone to…
Recent advancements in machine learning and adaptive cognitive systems are driving a growing demand for large and richly annotated multimodal data. A prominent example of this trend are fusion models, which increasingly incorporate multiple…
Industrial soft sensing is crucial for accurate process monitoring through reliable inference of dominant sensor variables. However, developing effective data-driven soft sensor models presents challenges, such as achieving domain…
GraphFlow is a visual workflow system designed to improve the reliability of agentic AI automation in multi-step, mission-critical processes. In these workflows, small errors compound rapidly: under an idealized model of independent steps,…
Recent advances in Vision Language Models (VLMs) have driven significant progress in visual reasoning. However, open-source VLMs still lag behind proprietary systems, largely due to the lack of high-quality reasoning data. Existing datasets…
Data-flow analyses like points-to analysis can vastly improve the precision of other analyses, and help perform powerful code optimizations. However, whole-program points-to analysis of large programs tend to be expensive - both in terms of…
Data-flow testing (DFT) aims to detect potential data interaction anomalies by focusing on the points at which variables receive values and the points at which these values are used. Such test objectives are referred as \emph{def-use…
Visual language such as charts and plots is ubiquitous in the human world. Comprehending plots and charts requires strong reasoning skills. Prior state-of-the-art (SOTA) models require at least tens of thousands of training examples and…
In this work, which is done in the context of a (moded) logic programming language, we devise a data-flow analysis dedicated to computing what we call argument profiles. Such a profile essentially describes, for each argument of a…