Feeds to Scour
SubscribedAll
Scoured 123516 posts in 35.9 ms
DominoTree/RuST: Example Rust/LLVM build toolchain for Atari TOS/EmuTOS (ST, Falcon030, TT030, etc) targets  🐧Rust for Linux
github.com·1d·Hacker News
Your parity gate must enforce the number you publish: a testing methodology for porting ML models across runtimes  🧪Jepsen Testing
dev.to·4d·DEV
BenchCAD: A Comprehensive, Industry-Standard Benchmark for Programmatic CAD  🎭Program Synthesis
arxiv.org·13h
Help needed! Seeking Contributors for a Pure C Compiler & Runtime · Issue #1  🔨Compiler Design
github.com·3d·Hacker News
Metal-Sci: A Scientific Compute Benchmark for Evolutionary LLM Kernel Search on Apple Silicon  📊Profile-Guided Optimization
arxiv.org·13h
PYTHALAB-MERA: Validation-Grounded Memory, Retrieval, and Acceptance Control for Frozen-LLM Coding Agents  💬Prompt Engineering
arxiv.org·13h
Assessing, Exploiting, and Mitigating Syntactic Robustness Failures in LLM-Based Code Generation  🏗️Cranelift
arxiv.org·1d
EvoPref: Multi-Objective Evolutionary Optimization Discovers Diverse LLM Alignments Beyond Gradient Descent  🎯Qdrant
arxiv.org·13h
RepoZero: Can LLMs Generate a Code Repository from Scratch?  🏗️Cranelift
arxiv.org·1d
CodeEvolve: LLM-Driven Evolutionary Optimization with Runtime-Enriched Target Selection for Multi-Language Code Enhancement  📊Profile-Guided Optimization
arxiv.org·5d
Delulu: A Verified Multi-Lingual Benchmark for Code Hallucination Detection in Fill-in-the-Middle Tasks  🤖TVM
arxiv.org·1d
PaT: Planning-after-Trial for Efficient Test-Time Code Generation  🎭Program Synthesis
arxiv.org·1d
Bridging Generation and Training: A Systematic Review of Quality Issues in LLMs for Code  🎭Program Synthesis
arxiv.org·4d
Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation  📱Edge AI
arxiv.org·1d
Coupling Models for One-Step Discrete Generation  ⚡Incremental Computation
arxiv.org·1d
Constraint Decay: The Fragility of LLM Agents in Backend Code Generation  🦙Ollama
arxiv.org·4d
Exploring Pass-Rate Reward in Reinforcement Learning for Code Generation  💬Prompt Engineering
arxiv.org·6d
AutoRAGTuner: A Declarative Framework for Automatic Optimization of RAG Pipelines  📊Performance Tools
arxiv.org·6d
Deep Graph-Language Fusion for Structure-Aware Code Generation  🍱Nom
arxiv.org·6d
Towards Reliable LLM Evaluation: Correcting the Winner's Curse in Adaptive Benchmarking  ⚡X-Fast Tries
arxiv.org·4d

Keyboard Shortcuts

Navigation

Next / previous item
j/k
Open post
oorEnter
Preview post
v

Post Actions

Love post
a
Like post
l
Dislike post
d
Undo reaction
u
Save / unsave
s

Recommendations

Add interest / feed
Enter
Not interested
x

Go to

Home
gh
Interests
gi
Feeds
gf
Likes
gl
History
gy
Changelog
gc
Settings
gs
Browse
gb
Search
/

General

Show this help
?
Submit feedback
!
Close modal / unfocus
Esc

Press ? anytime to show this help