GeezerVisonThe World Wide Web, restored to 800 pixels of glory. |
| Home|About|Gaming cabinet|Archives|How it works|Starter sites |
GeezerVison is showing github.com — Build software better, together
#
tmlrHere are 45 public repositories matching this topic...Language: All
Filter by language
Sort: Most stars
Sort options
An Attribute-based Method for Video Anomaly Detection (TMLR 2025)
[TMLR] Offical Implementation of ToMoE: ToMoE: Converting Dense Large Language Models to Mixture-of-Experts through Dynamic Structural Pruning
Official code for "ZigZag: Universal Sampling-free Uncertainty Estimation Through Two-Step Inference" (TMLR 2024)
computer-vision deep-learning neural-network pytorch uncertainty bayesian-inference uncertainty-quantification uncertainty-estimation icml robustness tmlr tmlr-2024 icml-2024
Official implementation of "Semantic-Drive": a local-first neuro-symbolic framework for long-tail AV data curation. We utilize open-vocabulary grounding (YOLOE) and multi-VLM consensus to mine safety-critical "Dark Data" within a consumer hardware compute budget.
machine-learning data-mining computer-vision pytorch object-detection autonomous-driving vlm nuscenes waymo-open-dataset data-centric-ai neuro-symbolic-ai large-language-models vision-language-model tmlr tmlr-2026
FORGE: Forward-Only Test-Time Adaptation for Integer-Only Vision Models on Microcontrollers (TMLR 2026)
microcontroller esp32 pytorch quantization int8 domain-adaptation edge-ai tinyml test-time-adaptation tmlr
[TMLR'26] PriSM: Prior-Guided Search Methods for Query Efficient Black-Box Adversarial Attacks
machine-learning thesis genetic-algorithm evolutionary-algorithms publication saliency-map robustness adversarial-machine-learning adversarial-examples cma-es adversarial-attacks bsc-thesis adversarial-robustness square-attack transfer-based-attacks tmlr machine-learning-robustness tmlr-2026
Code for 'Transport with Support: Data-Conditional Diffusion Bridges'
CRoPS (TMLR)
Priority-Constrained Descent (PCD) for hierarchical multi-objective optimization. Code for the TMLR 2026 paper.
sparsity deep-learning optimization pytorch constrained-optimization pruning multi-objective-optimization low-rank tmlr
TMLR 2026 | Mechanistic interpretability: attention-head binding (EB*) as a marker of concept emergence. 7 models, 5 architectures (Pythia 160M–2.8B, OLMo-1B, CRFM GPT-2, SmolLM3-3B, Qwen2.5-1.5B), 41 terms.
nlp accessibility transformers language-models pythia interpretability few-shot-learning training-dynamics attention-heads mechanistic-interpretability qwen tmlr olmo smollm3 tmlr-2026 concept-emergence crfm
Official TMLR implementation of representation-centric prompting for vision-language fusion
Reproducibility artifact for a study of how post-training quantization changes small language models' responses to misleading contextual cues. Frozen trial set, 15 generation files, 3,078 automated judgments, human annotation audit, and full analysis pipeline.
evaluation modal reproducibility quantization reasoning cot llm chain-of-thought faithfulness llm-evaluation tmlr deepseek small-language-models research-artifact
Reproducible benchmark for cold-start adaptability: measures cumulative errors while learning from scratch, not just final accuracy. Published in TMLR 2026.
benchmark machine-learning reproducible-research evaluation active-learning online-learning evaluation-framework tmlr tmlr-2026
Official code for the TMLR 2025 paper: "On Joint Regularization and Calibration in Deep Ensembles"
deep-learning pytorch calibration regularization uncertainty-quantification early-stopping temperature-scaling deep-ensembles tmlr
BalancedDPO (TMLR 2026): multi-metric alignment for text-to-image diffusion models — majority-vote consensus across preference metrics inside DPO.
Add this topic to your repoTo associate your repository with the tmlr topic, visit your repo's landing page and select "manage topics." |
| You are visitor 01402503 — GeezerVison does not store the pages you look up. Best viewed with Netscape Navigator 4.7 or Internet Explorer 6 at 800×600. No cookies required. |