🏗️ MLIR - nmarshall · Scour

DepthKV: Layer-Dependent KV Cache Pruning for Long-Context LLM Inference 💻Local LLMs

DryRUN: On the Role of Public Tests in LLM-Driven Code Generation ⚙️LLVM

RefEvo: Agentic Design with Co-Evolutionary Verification for Agile Reference Model Generation ∀Lean4

Resource-Lean Lexicon Induction for German Dialects 🤖Transformers

RealBench: A Repo-Level Code Generation Benchmark Aligned with Real-World Software Development Practices ⚙️LLVM

FormalScience: Scalable Human-in-the-Loop Autoformalisation of Science with Agentic Code Generation in Lean ∀Lean4

An Investigation of Linguistic Biases in LLM-Based Recommendations 💻Local LLMs

From If-Statements to ML Pipelines: Revisiting Bias in Code-Generation 🏭Code Generation

Aligned Multi-View Scripts for Universal Chart-to-Code Generation 🏭Code Generation

Learning Reasoning World Models for Parallel Code ⚙️Concurrency Models

Can Code Evaluation Metrics Detect Code Plagiarism? 🔍Static Analysis

Dialect vs Demographics: Quantifying LLM Bias from Implicit Linguistic Signals vs. Explicit User Profiles 💻Local LLMs

PhysCodeBench: Benchmarking Physics-Aware Symbolic Simulation of 3D Scenes via Self-Corrective Multi-Agent Refinement 🎲Procedural Generation

Do Synthetic Trajectories Reflect Real Reward Hacking? A Systematic Study on Monitoring In-the-Wild Hacking in Code Generation 🔓Binary Exploitation

From Natural Language to Verified Code: Toward AI Assisted Problem-to-Code Generation with Dafny-Based Formal Verification ∀Lean4

SSG: Logit-Balanced Vocabulary Partitioning for LLM Watermarking 💻Local LLMs

CharTide: Data-Centric Chart-to-Code Generation via Tri-Perspective Tuning and Inquiry-Driven Evolution 📐Diagramming

"This Wasn't Made for Me": Recentering User Experience and Emotional Impact in the Evaluation of ASR Bias 🗣️Speech Synthesis

Machine learning and digital pragmatics: Which word category influences emoji use most? 🤖Transformers

Extending Ruzzy with LibAFL 🐛Fuzzing

blog.trailofbits.com·1d·Hacker News

Log in to enable infinite scrolling