Opportunities

Automated Program Repair (APR) has witnessed significant progress with the advent of Large Language Models (LLMs). However, as modern software systems increasin

Code review is a cornerstone of software development, where reviewers provide feedback through written comments to ensure code quality, maintainability, and cor

Flow matching has emerged as an effective framework for learning complex data distributions, but adapting pretrained flow models to new tasks often requires com

In underwater covert cooperative missions, autonomous underwater vehicles (AUVs) often cannot rely on active sonar to continuously obtain complete information,

A language model may be asked either what experts believe about a contested claim or what it believes about the claim itself. A trustworthy conversational agent

Machine-learning force fields (MLFFs) are reliable only near their training distribution, making efficient construction of diverse training sets a major bottlen

Large language models (LLMs) write Unity C\# for game scenes. Yet nearly all demonstrations rest on an iterative repair loop that regenerates code until it comp

Safety alignment in large language models can be fragile under fine-tuning, as even benign task adaptation may increase harmful compliance. Existing defenses ma

This study examines feedback in English as a Foreign Language (EFL) writing contexts, focusing on written corrective feedback (WCF). Large language models (LLMs

Text-to-video (T2V) generators can synthesize realistic and temporally coherent videos, but controllably removing a target concept from a generator remains diff

Failure attribution for LLM-based agentic systems, i.e., identifying which steps in a failure trajectory caused the task to fail, is critical for debugging and

Large language models achieve strong scores on medical benchmarks, yet these benchmarks evaluate each question in isolation, providing no measure of whether a s

Docker is widely used to create reproducible build environments, but Dockerfile drift, the divergence between a Dockerfile and its evolving source code, can cau

Failure diagnosis in modern software systems requires iterative evidence acquisition and hypothesis reasoning guided by operational experience. Existing LLM-bas

Background. Large language models (LLMs) have become increasingly capable of understanding and generating source code, leading to their widespread adoption in s

Show HN: MemStitch – Zero-copy context bridging for vLLM (25x TTFT speedup)

Le CRM métier des agences immobilières françaises

Waku Waku! Waku agent is your personal AI agent, on your own laptop, in code you can read in an afternoon — harness + loop + memory + eval

Use LLMs to hide messages inside normal looking conversations

Jacobian-Brainwash : A manual alignment tool for large language models built on Anthropic's Jacobian Lens. Results are exportable.