Opportunities

Recent advances in large language models (LLMs) and their extension to vision-language models (VLMs) have made it easier to combine text and images for tasks su

Sign language is a primary communication channel for millions of Deaf and hard-of-hearing people, yet text-to-signer video generation remains costly because vid

LLM-based agents have rapidly improved at operating individual digital environments such as mobile applications, desktop systems, and smart homes. However, real

This paper examines fairness and accountability in global software development by focusing on how competence is assessed and valued across unequal regional cont

Modern coding agents expose multiple tool surfaces -- IDE primitives, bash, and Model Context Protocol (MCP) code-execution -- and the field has shipped three c

Recent advances in 3D human reconstruction have improved overall performance, yet current models still fail in the most challenging real-world scenarios. They o

Sandboxing remains a core technique for observing suspicious program behavior, yet environment-aware malware increasingly suppresses execution when analysis is

Large language models (LLMs) exhibit a well-documented gap between latent capability and consistent activation: the router hypothesis posits that models possess

Large Language Models (LLMs) are increasingly used for code smell detection tasks due to their ability to interpret program semantics. However, their reliabilit

Personal AI assistants on mobile and wearable devices continuously perceive users' daily lives through visual and audio streams. However, answering queries abou

Graph retrieval-augmented generation (GraphRAG) enhances large language models with structured knowledge, yet existing systems construct knowledge graphs in a s

What happens to an LLM agent's tool choice when the reliable tool silently changes within an ongoing session? We borrow set-shifting from cognitive psychology t

Multi-agent and memory-augmented LLM systems often place coordination content, shared state, prior discussion, tool outputs, summaries, and role instructions, i

Large language models (LLMs) have achieved remarkable performance on high-school and olympiad-style mathematics, yet their capabilities on advanced mathematics

Defect segmentation in additive manufacturing (AM) X-ray computed tomography (XCT) images remains challenging due to severe class imbalance and large distributi

Directed fuzzing steers fuzzers toward user-defined sink functions to identify vulnerabilities, but it frequently fails to trigger crashes even after long campa

We advocate for AI/ML issue resolution frameworks tailored to maintenance workflows and the nature of modern AI/ML systems. Existing issue resolution frameworks

Show HN: Introducing: Zotfile Agents

Show HN: LoopGain – Stop agent loops with control theory, not max_iterations

understory — memory that grows. Self-wiring, plain-markdown memory for AI agents (MCP + local models + a living graph).