computer vision

IterCAD: Iterative Program Repair for CAD Code Generation from Orthographic Views

This paper proposes IterCAD, an iterative framework that reformulates orthographic-view-to-CAD generation as a progressive program repair process that consistently improves code executability and geometric fidelity over strong one-shot baselines.

TransSLR: A Lightweight Transformer for Sign Language Recognition

This work proposes TransSLR, a lightweight Temporal Transformer Encoder trained from scratch on 64-frame normalized pose sequences, with average pooling and a classification head that achieves signer-independent generalization without relying on visual appearance on the CASL-W60 benchmark.

AnchorPrune: Relevance-Anchored Contextual Expansion for Visual Token Pruning

AnchorPrune is a training-free framework that first constructs a protected relevance anchor and then expands it with complementary visual context, establishing relevance-anchored contextual expansion as an effective principle for efficient multimodal inference.

Three Necessary Principles for Self-Supervised Visual Representation Learning

We argue that learning visual representations without labels requires a training signal jointly complete across three non-overlapping objectives: semantic invariance across augmented views, patch-level spatial prediction, and representational non-degeneracy. We formalize these as the observation, prediction, and regula...

CodePori: Large-Scale System for Autonomous Software Development Using Multi-Agent Technology

While LLM-based multi-agent systems show potential for large-scale software development, successful integration requires addressing challenges such as memory limitations, hallucinations, and code smells, alongside a practitioner-centric perspective.

Can Large Language Models Serve as Data Analysts? A Multi-Agent Assisted Approach for Qualitative Data Analysis

The proposed LLM-based multi-agent system automates qualitative data analysis process, creating opportunities for researchers and practitioners, and future improvements focus on enhancing multilingual performance and integrating continuous expert feedback.

Engineering a Governance-Aware AI Sandbox: Design, Implementation, and Lessons Learned

This work designs and operationalizes a governance-aware, multi-tenant AI sandbox that supports structured experimentation and produces reusable evaluation evidence across stakeholders and yields lessons learned and practical considerations that inform deployment and future evolution of governance-aware sandbox platfor...

TERE4AI: A Knowledge Graph-Based Tool for Generating EU AI Act Compliant Requirements

AI Sandbox: Technical Report

This work presents the design and implementation of a governance-aware, multi-tenant AI sandbox for structured experimentation and the generation of reusable evaluation evidence across projects and stakeholder groups.

LLM-Based Multi-Agent Systems for Code Generation: A Multi-Vocal Literature Review

A Multi-Vocal Literature Review is conducted, combining insights from both academia and industry, including peer-reviewed studies and grey literature to systematically synthesize and analyze existing knowledge on LLM-based multi-agent systems for code generation.

Agentic Frameworks for Reasoning Tasks: An Empirical Study

This study provides the first large-scale empirical comparison of agentic frameworks for reasoning-intensive software engineering tasks and shows that framework selection should prioritize orchestration quality, especially memory control, failure handling, and cost management.

Autonomous Agents in Software Development: A Vision Paper

The vision is to leverage the capabilities of multiple GPT agents to contribute to SE tasks and to propose an initial road map for future work, arguing that multiple G PT agents can perform creative and demanding tasks far beyond coding and debugging.