| EfficientRollout: System-Aware Self-Speculative Decoding for RL Rollouts added by Syntology |
2026-06 (from id) |
furiosa-ai/EfficientRollout/sd_toggle/fit.py 5ed7d80f88d8f831 |
ran
|
Apache-2.0 (permissive) |
| Opportunistic Target Selection: Early Directional Commitment for Query-Efficient Black-Box Adversarial Attacks added by Syntology |
2026-05 (from id) |
Tariolle/opportunistic-target-selection/analysis/analyze_lockmatch.py 7e89e69f7971931c |
ran
|
MIT (permissive) |
| Scientific Theory of a Black-Box: A Life Cycle-Scale XAI Framework Based on Constructive Empiricism added by Syntology |
2026-02 (from id) |
semueller/stobb_cobot/show_example.py d403a53e43a72df5 |
unverified |
no licence file found · pointer only |
| UniFinEval: Towards Unified Evaluation of Financial Multimodal Models across Text, Images and Videos added by Syntology |
2026-01 (from id) |
aifinlab/UniFinEval/evaluate_py/data_loader.py 80031dd34b37c131 |
unverified |
Apache-2.0 (permissive) |
| Private Prediction via PAC Privacy added by Syntology |
2026-01 (from id) |
zhxchd/pac/benchmark/pac_microbench/analyze_results.py 8ed50327556b3ce0 |
unverified |
AGPL-3.0 (copyleft) · pointer only |
| PruneCD: Contrasting Pruned Self Model to Improve Decoding Factuality added by Syntology |
2025-09 (from id) |
hoeng4/PruneCD/1_factual_layer_search/tfqa_mc.py 2a4c0ecd291e1795 |
unverified |
no licence file found · pointer only |
| PruneCD: Contrasting Pruned Self Model to Improve Decoding Factuality added by Syntology |
2025-09 (from id) |
hoeng4/PruneCD/2_benchmark/1_tfqa_gen.py a35a1be39e4bef73 |
unverified |
no licence file found · pointer only |
| PruneCD: Contrasting Pruned Self Model to Improve Decoding Factuality added by Syntology |
2025-09 (from id) |
hoeng4/PruneCD/2_benchmark/3_4_triviaqa_natural_questions.py 872f1d147b70aced |
unverified |
no licence file found · pointer only |
| Expanding before Inferring: Enhancing Factuality in Large Language Models through Premature Layers Interpolation |
3 Jun 2025 |
CuSO4-Chen/PLI/src/evaluation/truthfulqa_eval.py 2a4c0ecd291e1795 |
unverified |
MIT (permissive) |
| arXiv:2504.04635 |
2025-04 (from id) |
patqdasilva/steering-off-course/DoLa/factor_eval.py 78392b8414df821e |
ran · our draft was wrong
|
MIT (permissive) |
| arXiv:2504.04635 |
2025-04 (from id) |
patqdasilva/steering-off-course/DoLa/tfqa_mc_eval.py 2a4c0ecd291e1795 |
unverified |
MIT (permissive) |
| arXiv:2504.04635 |
2025-04 (from id) |
patqdasilva/steering-off-course/DoLa/tfqa_eval.py a35a1be39e4bef73 |
unverified |
MIT (permissive) |
| SLED: Self Logits Evolution Decoding for Improving Factuality in Large Language Models |
1 Nov 2024 |
JayZhang42/SLED/utils/utils_factor.py 78392b8414df821e |
ran · our draft was wrong
|
no licence file found · pointer only |
| Normalization Layer Per-Example Gradients are Sufficient to Predict Gradient Noise Scale in Transformers |
1 Nov 2024 |
cerebrasresearch/nanogns/exact/csv_tools.py f3552f440f4a76f3 |
unverified |
no licence file found · pointer only |
| BenTo: Benchmark Task Reduction with In-Context Transferability |
17 Oct 2024 |
tianyi-lab/bento/benchmark-reduction/analysis_compare_methods_.py a4439ebb3e6536fd |
ran
|
Apache-2.0 (permissive) |
| BenTo: Benchmark Task Reduction with In-Context Transferability |
17 Oct 2024 |
tianyi-lab/bento/benchmark-reduction/analysis_compare_methods_flan.py 1b7a6ef6b06e147c |
ran
|
Apache-2.0 (permissive) |
| BenTo: Benchmark Task Reduction with In-Context Transferability |
17 Oct 2024 |
tianyi-lab/bento/benchmark-reduction/analysis.py 5caec032cc3549d1 |
ran
|
Apache-2.0 (permissive) |
| U-shaped and Inverted-U Scaling behind Emergent Abilities of Large Language Models |
2 Oct 2024 |
tony10101105/ExpEmergence/evaluation/abstract_narrative_understanding/abstract_narrative_understanding_question_grouping.py dbdc88cccaa015e1 |
ran
|
MIT (permissive) |
| Improving Factuality in Large Language Models via Decoding-Time Hallucinatory and Truthful Comparators |
22 Aug 2024 |
ydk122024/cdt/src/benchmark_evaluation/truthfulqa_eval.py 2a4c0ecd291e1795 |
unverified |
MIT (permissive) |
| In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation |
3 Mar 2024 |
hkust-nlp/activation_decoding/eval_tqa.py 297c84ffca2864db |
ran · our draft was wrong
|
no licence file found · pointer only |
| SH2: Self-Highlighted Hesitation Helps You Decode More Truthfully |
11 Jan 2024 |
0-kaikai-0/sh2/tfqa_keys.py 2a4c0ecd291e1795 |
unverified |
no licence file found · pointer only |
| SH2: Self-Highlighted Hesitation Helps You Decode More Truthfully |
11 Jan 2024 |
0-kaikai-0/sh2/factor_eval.py c47f09f5ffb69e69 |
unverified |
no licence file found · pointer only |
| SH2: Self-Highlighted Hesitation Helps You Decode More Truthfully |
11 Jan 2024 |
0-kaikai-0/sh2/tfqa_mc_eval.py 91ad5d3cac5d67de |
unverified |
no licence file found · pointer only |
| Alleviating Hallucinations of Large Language Models through Induced Hallucinations |
25 Dec 2023 |
hillzhang1999/icd/src/benchmark_evaluation/truthfulqa_eval.py 2a4c0ecd291e1795 |
unverified |
MIT (permissive) |
| Is Bigger and Deeper Always Better? Probing LLaMA Across Scales and Layers |
7 Dec 2023 |
nuochenpku/llama_analysis/factural_eval.py 2a4c0ecd291e1795 |
unverified |
no licence file found · pointer only |
| Corrupting Neuron Explanations of Deep Visual Features |
25 Oct 2023 |
Trustworthy-ML-Lab/corrupting_neuron_explanations/network-dissection/loader/data_loader.py c8b1a48d7aa8bf6a |
ran
|
MIT (permissive) |
| DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models |
7 Sep 2023 |
voidism/DoLa/factor_eval.py 78392b8414df821e |
ran · our draft was wrong
|
no licence file found · pointer only |
| Still No Lie Detector for Language Models: Probing Empirical and Conceptual Roadblocks |
30 Jun 2023 |
balevinstein/probes/Train_CCSProbe.py 490da4aec73c34bb |
ran · our draft was wrong
|
MIT (permissive) |
| Are we certain it's anomalous? |
16 Nov 2022 |
aleflabo/HypAD/utils/data.py 7996920fef9af9d0 |
unverified |
MIT (permissive) |
| Are Large Pre-Trained Language Models Leaking Your Personal Information? |
25 May 2022 |
jeffhj/lm_personalinfoleak/pred.py 16b6899a69cd97b7 |
unverified |
Apache-2.0 (permissive) |
| Graph-Augmented Normalizing Flows for Anomaly Detection of Multiple Time Series |
16 Feb 2022 |
D3-AI/Orion/orion/data.py 04aff2c366db2eed |
unverified |
MIT (permissive) |
| Modeling Human Exploration Through Resource-Rational Reinforcement Learning |
27 Jan 2022 |
marcelbinz/resource-rational-reinforcement-learning/utils.py e19e1433392eca4e |
ran · our draft was wrong
|
no licence file found · pointer only |
| Is Someone Speaking? Exploring Long-term Temporal Features for Audio-visual Active Speaker Detection |
14 Jul 2021 |
TaoRuijie/TalkNet_ASD/utils/get_ava_active_speaker_performance.py bdc52ecccc77b9e1 |
unverified |
MIT (permissive) |
| Neural Distributed Source Coding |
5 Jun 2021 |
acnagle/neural-dsc/plot_rd_curves.py 9a3b377007d57821 |
unverified |
MIT (permissive) |
| Unsupervised Learning from Video with Deep Neural Embeddings |
28 May 2019 |
neuroailab/VIE/build_data/kinetics/download_videos.py 03177c36e1973e33 |
ran · our draft was wrong
|
no licence file found · pointer only |
| Continuous Hierarchical Representations with Poincaré Variational Auto-Encoders |
17 Jan 2019 |
emilemathieu/pvae/pvae/datasets/datasets.py a8eb4a941274e36a |
unverified |
MIT (permissive) |
| Deep Reinforcement Learning for Imbalanced Classification |
5 Jan 2019 |
Denbergvanthijs/imbDRL/imbDRL/data.py 692b71a43ff1f48c |
unverified |
Apache-2.0 (permissive) |
| arXiv:aaai_6793 |
|
activitynet/ActivityNet/Evaluation/get_ava_active_speaker_performance.py 2b0fca044dd4be81 |
unverified |
MIT (permissive) |
| arXiv:aaai_19900 |
|
cg1177/DCAN/dcan_anet/Eval/get_ava_active_speaker_performance.py c277623807229f9f |
unverified |
Apache-2.0 (permissive) |
| arXiv:2024.findings-naacl.294 |
|
balevinstein/Probes/Train_CCSProbe.py 490da4aec73c34bb |
ran · our draft was wrong
|
MIT (permissive) |