Tags

This is a map of 32 tags over 29 entries (papers, posts, slides, and posters). Larger nodes mark recurring themes; lines show papers, posts, slides, and posters sharing those themes.

Tags32
Entries (notes) 29
Links140
LargestLLMs

Tag Entry Atlas

Tag and entry networkThe largest tag nodes sit near the center. Outer nodes are entries. Lines connect entries to their tags.Researc: Medical Image Spatial Grounding with Semantic SamplingResearc: Ranking Reasoning LLMs under Test-Time ScalingResearc: Don't Pass@k: A Bayesian Framework for Large Language Model EvaluationResearc: Quantize What Counts: More for Keys, Less for ValuesResearc: 70% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length FloatPost: Entropy of bfloat16 During Training: How Optimizers Shape Weight DistributionsPost: Entropy of bfloat16: 8 Bits Are Doing 2.6 Bits of WorkPost: Simulating LLM Evaluation Datasets Using Psychometric ModelsPost: Simulating LLM Answers to Evaluation DatasetsSlide: Medical Image Spatial Grounding with Semantic SamplingSlide: Ranking Reasoning LLMs under Test-Time ScalingSlide: Quantize What Counts: More for Keys, Less for ValuesSlide: Serving Reasoning LLMs Efficiently and ReliablySlide: Serving Reasoning LLMs Efficiently and Reliably [No Anime]Slide: Python EnvironmentsSlide: Don't Pass@k: A Bayesian Framework for Large Language Model EvaluationSlide: LLM Research DirectionsSlide: Virtual Agentic Lab!Slide: Tool Use (Function Calling) & RAGSlide: State of Large Language ModelsSlide: 70% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length FloatSlide: Test-Time Scaling Under BudgetSlide: Psychometric Modeling of LLM Evaluation DatasetsSlide: Reasoning in Large Language ModelsPoster: Medical Image Spatial Grounding with Semantic SamplingPoster: Quantize What Counts: More for Keys, Less for ValuesPoster: Ranking Reasoning LLMs under Test-Time ScalingPoster: Don't Pass@k: A Bayesian Framework for Large Language Model EvaluationPoster: 70% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length FloatLLMs: 19 entriesLLMsBayesian: 10 entriesBayesianBenchmarking: 10 entriesBenchmarkingEfficiency: 9 entriesEfficiencyInference: 9 entriesInferenceTest-Time Scaling: 9 entriesTest-Time ScalingCompression: 6 entriesCompressionQuantization: 6 entriesQuantizationReasoning: 5 entriesReasoningScorio: 5 entriesScorioEvaluation: 4 entriesEvaluationInformation Theory: 4 entriesInformation TheoryLLM Evaluation: 4 entriesLLM EvaluationGPU: 3 entriesGPUKV Cache: 3 entriesKV CacheLLM Ranking: 3 entriesLLM RankingLossless: 3 entriesLosslessMedical Imaging: 3 entriesSimulation: 3 entriesSpatial Grounding: 3 entriesVision-Language Models: 3 entriesAI: 2 entriesRAG: 2 entriesStatistics: 2 entriesTheory: 2 entriesTools: 2 entriesAgents: 1 entriesDatasets: 1 entriesOptimizers: 1 entriesReasoning Models: 1 entries
Research Posts Slides Posters

Signal

The strongest tags and pairings show where the archive has accumulated repeated work.

LLMs 3 research / 3 posts / 11 slides / 2 posters
19 Bayesian 2 research / 6 slides / 2 posters
10 Benchmarking 2 research / 5 slides / 3 posters
10 Efficiency 2 research / 1 posts / 4 slides / 2 posters
9 Inference 2 research / 1 posts / 4 slides / 2 posters
9 Test-Time Scaling 2 research / 5 slides / 2 posters
9 Compression 1 research / 2 posts / 2 slides / 1 posters
6 Quantization 1 research / 4 slides / 1 posters
6 Reasoning 1 research / 1 posts / 3 slides
5 Scorio 1 research / 2 slides / 2 posters
5
Bayesian + Test-Time Scaling shared entries 9 LLMs + Efficiency shared entries 9 LLMs + Inference shared entries 9 Bayesian + Benchmarking shared entries 7 Benchmarking + Test-Time Scaling shared entries 7 Efficiency + Inference shared entries 7 LLMs + Quantization shared entries 6 Bayesian + Scorio shared entries 5

All Tags

Agents 1 AI 2 Bayesian 10 Benchmarking 10 Compression 6 Datasets 1 Efficiency 9 Evaluation 4 GPU 3 Inference 9 Information Theory 4 KV Cache 3 LLM Evaluation 4 LLM Ranking 3 LLMs 19 Lossless 3 Medical Imaging 3 Optimizers 1 Quantization 6 RAG 2 Reasoning 5 Reasoning Models 1 Scorio 5 Simulation 3 Spatial Grounding 3 Statistics 2 Test-Time Scaling 9 Theory 2 Tools 2 Training 1 Tutorial 1 Vision-Language Models 3