| AgentKV: Phase-Aware KV Eviction for Agentic LLMs added by Syntology |
2026-09 (from id) |
LiuTaowen-Tony/agentkv/experiment/runners/bfcl.py 8c62fac91d309ed8 |
unverified |
Apache-2.0 (permissive) |
| AgentKV: Phase-Aware KV Eviction for Agentic LLMs added by Syntology |
2026-09 (from id) |
LiuTaowen-Tony/agentkv/experiment/runners/tau2.py 9e4112999274379f |
unverified |
Apache-2.0 (permissive) |
| Import What You Need: Learning When and How to Augment EHR Graphs with External Knowledge added by Syntology |
2026-09 (from id) |
ChenC2002/ReTA/reta/knowledge/release.py 0b64df57e6173100 |
unverified |
no licence file found · pointer only |
| BVR Sim: An Open and High-Throughput Environment for Heterogeneous Air-Combat Reinforcement Learning added by Syntology |
2026-08 (from id) |
lizi-Margin/bvr_sim/bvr_sim_rl/ppo.py 28689982c3c87971 |
unverified |
GPL-3.0 (copyleft) · pointer only |
| KSE-Web: An Analysis of Hybrid Retrieval and LLM-Assisted Query Expansion for Low-Resource Khmer Semantic Search added by Syntology |
2026-08 (from id) |
back-kh/Khmer-Semantic-Search/codes/evaluate_retrieval.py b84f26eda680ba83 |
unverified |
MIT (permissive) |
| No Task Fails Every Time: Why One-Shot Audits Are Structurally Blind to Agent Damage added by Syntology |
2026-08 (from id) |
shivenkk/agentrelbench/src/agentrelbench/inner_runner.py b401e33d37927494 |
unverified |
Apache-2.0 (permissive) |
| StepJack: Benchmarking Computer-Use Agent Safety Against Multi-Step Indirect Prompt Injection added by Syntology |
2026-08 (from id) |
BorealisAI/StepJack/auto_decomp/iterative_refinement.py cc25050cda173203 |
unverified |
GPL-3.0 (copyleft) · pointer only |
| Passing Coarse Marginal Checks Can Be Cheap: Persona Mixtures and Imprecise Treatment-Response Estimates in an LLM Persona Panel added by Syntology |
2026-08 (from id) |
yoheinakajima/synthetic-players/artifacts/api-server/engine/freeze_lint.py ddd3209334fa1bad |
unverified |
licence not identified · pointer only |
| Metaphor Tracer: A Theory-Informed Analysis of Hidden States added by Syntology |
2026-07 (from id) |
HermeneuticAI/MetaphorTracer/structural_attractor_scanV2.py 1d187e5adf3abcce |
unverified |
licence not identified · pointer only |
| Rethinking Self-Evolution: A Constrained Exploration-Exploitation Process for Mitigating Skill Overfitting added by Syntology |
2026-07 (from id) |
HQ-Lin/SkillBoost/src/skillboost/evolve.py ff93879d3f1270a5 |
unverified |
MIT (permissive) |
| WorkSurface-Bench: Benchmarking Enterprise Agents on Multi-Surface Knowledge Routing added by Syntology |
2026-07 (from id) |
haolpku/WorkSurface-Bench/worksurface/derive_tasks.py 662806b1db61b796 |
unverified |
Apache-2.0 (permissive) |
| Auditing Alignment Controllability in LLMs via Political Axes added by Syntology |
2026-07 (from id) |
mbrcic/llm-political-steerability/ingestion/01_collect/bundle_compound_pilot_raw.py 3f00153f9d94c3f2 |
unverified |
MIT (permissive) |
| Auditing Alignment Controllability in LLMs via Political Axes added by Syntology |
2026-07 (from id) |
mbrcic/llm-political-steerability/ingestion/01_collect/bundle_compound_pilot_scty_raw.py bec89bcd5c26b16a |
unverified |
MIT (permissive) |
| Remedying Coarsening-Based GNN Training under Heterophily via Adaptive Complementary Enhancement added by Syntology |
2026-07 (from id) |
vasile-paskardlgm/ACE/refined_projector.py fae6ee332c2fa1b7 |
unverified |
no licence file found · pointer only |
| LFM: Leveraging Foundation Models for Source-Free Universal Domain Adaptation added by Syntology |
2026-07 (from id) |
iamjingli/LFM/train_target.py 51b1a343a1c5c316 |
unverified |
MIT (permissive) |
| PsiLogic: Chaos-Aware Active Cancellation for Adam with a Fair Cross-Domain Benchmark added by Syntology |
2026-07 (from id) |
Troxter222/psilogic/benchmark_nlp_5000_psilogic.py 4055d49d30e44912 |
unverified |
MIT (permissive) |
| Operator-Aware Mixed-Precision Tolerance Calibration for Tensor Kernels added by Syntology |
2026-07 (from id) |
sarkar-dipankar/gpuemu-corpus/analysis/p2_calibrate.py a474017039931f46 |
ran · metamorphic tier: well formed
|
no licence file found · pointer only |
| When Does Restricting a Coding Agent to execute_code Help? A Regime × Agent-Design Ablation added by Syntology |
2026-07 (from id) |
hyang0129/onlycodes/paper/lint.py 19cc996c6da2baf9 |
unverified |
no licence file found · pointer only |
| When Does Restricting a Coding Agent to execute_code Help? A Regime × Agent-Design Ablation added by Syntology |
2026-07 (from id) |
hyang0129/onlycodes/swebench/_artifact_grade_runner.py 9c3a8620e1fa9c13 |
unverified |
no licence file found · pointer only |
| Large-scale dataset of automatically classified rhetorical sections in scientific papers added by Syntology |
2026-07 (from id) |
daniel-verdi/section-splitter/section_classifier.py da7bfb7eb2774dd8 |
unverified |
no licence file found · pointer only |
| TraceLab: Characterizing Coding Agent Workloads for LLM Serving added by Syntology |
2026-06 (from id) |
uw-syfi/TraceLab/artifacts/utils/png_sidecar.py 9751953fbd7bb868 |
unverified |
Apache-2.0 (permissive) |
| Faults in Our Formal Benchmarking: Dataset Defects and Evaluation Failures in Lean Theorem Proving added by Syntology |
2026-06 (from id) |
leanprover/lean4/script/gen_constants_cpp.py 687def3c02ea528c |
ran
|
Apache-2.0 (permissive) |
| Faults in Our Formal Benchmarking: Dataset Defects and Evaluation Failures in Lean Theorem Proving added by Syntology |
2026-06 (from id) |
leanprover/lean4/script/gen_tokens_cpp.py 193ca90e21e7f2eb |
ran
|
Apache-2.0 (permissive) |
| Model Forensics: Investigating Whether Concerning Behavior Reflects Misalignment added by Syntology |
2026-06 (from id) |
gkroiz/agent-interp-envs/environments/code_summary_honesty/run_eval.py 1cc1526945db6851 |
unverified |
MIT (permissive) |
| PACT: Self-Evolving Physical Safety Alignment for Diffusion Policies in Embodied Manipulation added by Syntology |
2026-06 (from id) |
robotwin-Platform/RoboTwin/code_gen/task_generation.py 39b0deb7b86b112d |
unverified |
MIT (permissive) |
| PACT: Self-Evolving Physical Safety Alignment for Diffusion Policies in Embodied Manipulation added by Syntology |
2026-06 (from id) |
robotwin-Platform/RoboTwin/code_gen/task_generation_mm.py 0712e9a6f1819e1d |
unverified |
MIT (permissive) |
| PACT: Self-Evolving Physical Safety Alignment for Diffusion Policies in Embodied Manipulation added by Syntology |
2026-06 (from id) |
robotwin-Platform/RoboTwin/code_gen/task_generation_simple.py ab268ff8e80c132c |
unverified |
MIT (permissive) |
| TARPO: Token-Wise Latent-Explicit Reasoning via Action-Routing Policy Optimization added by Syntology |
2026-06 (from id) |
unslothai/unsloth/docker/unsloth_nb_content_sig.py 6b380b9c888dc9d8 |
unverified |
Apache-2.0 (permissive) |
| TARPO: Token-Wise Latent-Explicit Reasoning via Action-Routing Policy Optimization added by Syntology |
2026-06 (from id) |
unslothai/unsloth/docker/unsloth_nb_strip_colab.py 97ce574c0c7a8f63 |
unverified |
Apache-2.0 (permissive) |
| SEAOTTER: Sensor Embedded Autoencoding with One-Time Transcode for Efficient Reconstruction added by Syntology |
2026-06 (from id) |
UT-SysML/seaotter/src/seaotter/eval/encode_complexity.py cca8f4086ee700d3 |
unverified |
no licence file found · pointer only |
| Forecasting Conceptual Diffusion in Science: The Case of Quantum Computing added by Syntology |
2026-06 (from id) |
wazaahhh/breakthroughs-diffusion/pipeline/sub117_compare.py 1033bdf6627a64dd |
ran
|
licence not identified · pointer only |
| Forecasting Conceptual Diffusion in Science: The Case of Quantum Computing added by Syntology |
2026-06 (from id) |
wazaahhh/breakthroughs-diffusion/pipeline/index_snapshot.py 4a813ada24e52bdc |
unverified |
licence not identified · pointer only |
| Forecasting Conceptual Diffusion in Science: The Case of Quantum Computing added by Syntology |
2026-06 (from id) |
wazaahhh/breakthroughs-diffusion/pipeline/run_subdomain.py 78be75c1b1451a79 |
unverified |
licence not identified · pointer only |
| Forecasting Conceptual Diffusion in Science: The Case of Quantum Computing added by Syntology |
2026-06 (from id) |
wazaahhh/breakthroughs-diffusion/pipeline/sub71_compare.py d9d1e65c3f28a160 |
unverified |
licence not identified · pointer only |
| Explainable Forecasting of Scientific Breakthroughs from Concept Network Dynamics added by Syntology |
2026-06 (from id) |
wazaahhh/breakthroughs-forecasting/pipeline/sub117_compare.py 1033bdf6627a64dd |
ran
|
no licence file found · pointer only |
| Explainable Forecasting of Scientific Breakthroughs from Concept Network Dynamics added by Syntology |
2026-06 (from id) |
wazaahhh/breakthroughs-forecasting/pipeline/index_snapshot.py 4a813ada24e52bdc |
unverified |
no licence file found · pointer only |
| Explainable Forecasting of Scientific Breakthroughs from Concept Network Dynamics added by Syntology |
2026-06 (from id) |
wazaahhh/breakthroughs-forecasting/pipeline/run_subdomain.py 78be75c1b1451a79 |
unverified |
no licence file found · pointer only |
| Rethinking Evaluation Paradigms in IBP-based Certified Training added by Syntology |
2026-06 (from id) |
ADA-research/CTRAIN/CTRAIN/install_git_dependencies.py 0fc1a98116d544e4 |
ran
|
MIT (permissive) |
| Sandboxed Coding Agents are Competitive Omni-modal Task Solvers added by Syntology |
2026-06 (from id) |
Dongping-Chen/OmniCoding/src/omnicoding/rl/run_trajectory.py 90c11597a7c38f09 |
unverified |
licence not identified · pointer only |
| Analyzing Quality-Latency-Resource Trade-offs in a Technical Documentation RAG Assistant Using LoRA Adaptation added by Syntology |
2026-05 (from id) |
EugPal/rag-lora-tradeoffs/src/data_pipeline/build_kubernetes_qa_dataset.py db5a7fb870b0bea9 |
unverified |
MIT (permissive) |
| Invariant-Based Weight Sharing for Message Passing added by Syntology |
2026-05 (from id) |
fseiffarth/SimpleGNN/src/simplegnn/utils/lrgb_splits.py 7ec64e6104befe90 |
unverified |
Apache-2.0 (permissive) |
| What Twelve LLM Agent Benchmark Papers Disclose About Themselves: A Pilot Audit and an Open Scoring Schema added by Syntology |
2026-05 (from id) |
mahdinaser/reprobe-audit/score_corpus.py 2361a1729fd5ac46 |
ran
|
MIT (permissive) |
| Prompt Compression for Diffusion Large Language Models: An Empirical Evaluation of LLMLingua-2 and LLaDA added by Syntology |
2026-05 (from id) |
axxx129-ops/DLLM-Compression/evaluation/check_exact_match.py c67ec6398e695ef0 |
ran
|
no licence file found · pointer only |
| A Deep Risk Estimator for Known Operator Learning added by Syntology |
2026-05 (from id) |
akmaier/KnownOperatorCT/src/fc_ko_sample_efficiency.py 5e43fdee48655eb5 |
unverified |
MIT (permissive) |
| HyperEyes: Dual-Grained Efficiency-Aware Reinforcement Learning for Parallel Multimodal Search Agents added by Syntology |
2026-05 (from id) |
DeepExperience/HyperEyes/RL/relax-hypereyes/Relax/.pre-commit-hooks/check_conflict_markers.py c25120c9239a61ab |
ran
|
no licence file found · pointer only |
| Vesselpose: Vessel Graph Reconstruction from Learned Voxel-wise Direction Vectors in 3D Vascular Images added by Syntology |
2026-05 (from id) |
Kainmueller-Lab/Vesselpose/vector/vector_generation.py 14d2110d81843986 |
unverified |
MIT (permissive) |
| Representation-Guided Parameter-Efficient LLM Unlearning added by Syntology |
2026-04 (from id) |
sustech-nlp/ReGLU/src/reglu/validation.py 1045e5778dc8f70b |
unverified |
licence not identified · pointer only |
| Self-evolving AI agents for protein discovery and directed evolution added by Syntology |
2026-03 (from id) |
ai4protein/VenusFactory2/install.py 20079f2e4d7b2523 |
unverified |
licence not identified · pointer only |
| Policy-Guided World Model Planning for Language-Conditioned Visual Navigation added by Syntology |
2026-03 (from id) |
AmirhoseinCh/PiJEPA/jepa_wms/app/scaffold.py 2004d0e6ae873f2e |
unverified |
MIT (permissive) |
| Less Data, Faster Convergence: Goal-Driven Data Optimization for Multimodal Instruction Tuning added by Syntology |
2026-03 (from id) |
rujiewu/GDO/gdo/extract_six_metrics.py 3968b3aa5d9e95e8 |
unverified |
MIT (permissive) |
| An Extreme Multi-label Text Classification (XMTC) Library Dataset: What if we took "Use of Practical AI in Digital Libraries" seriously? added by Syntology |
2026-03 (from id) |
sciknoworg/tib-sid/library-records-dataset/data-analysis/analysis3/gnd_embed_and_polysemy.py 3549bc73614fe724 |
unverified |
CC-BY-4.0 · pointer only |
| BayesFlow 2: Multi-Backend Amortized Bayesian Inference in Python added by Syntology |
6 Feb 2026 |
bayesflow-org/bf2-paper-case-study/case-study.py 7bb03261008ef54e |
unverified |
no licence file found · pointer only |
| SWE-Master: Unleashing the Potential of Software Engineering Agents via Post-Training added by Syntology |
2026-02 (from id) |
RUCAIBox/SWE-Master/R2E-Gym/SWE-smith/swesmith/bug_gen/get_cost.py 241ab2afb5b092fe |
unverified |
MIT (permissive) |
| Reward-free Alignment for Conflicting Objectives added by Syntology |
2026-02 (from id) |
PeterLauLukChen/RACO/eval/new_score.py 9072e64887215a81 |
unverified |
Apache-2.0 (permissive) |
| Reward-free Alignment for Conflicting Objectives added by Syntology |
2026-02 (from id) |
PeterLauLukChen/RACO/eval/new_score_beaver.py 78304958ed3d9382 |
unverified |
Apache-2.0 (permissive) |
| Reward-free Alignment for Conflicting Objectives added by Syntology |
2026-02 (from id) |
PeterLauLukChen/RACO/eval/vllm_generate_and_score.py 0591481280db58e2 |
unverified |
Apache-2.0 (permissive) |
| R3G: A Reasoning-Retrieval-Reranking Framework for Vision-Centric Answer Generation added by Syntology |
2026-02 (from id) |
czh24/R3G/src/pipeline.py 288113dc9b24b8e9 |
unverified |
no licence file found · pointer only |
| Are Whitepaper Claims Reflected in Market Structure? A Contamination-Aware Pipeline and a Power-Limited Null added by Syntology |
2026-01 (from id) |
studiofarzulla/whitepaper-claims/src/alignment/matched_dimension_analysis.py ac707b13d276c29b |
unverified |
licence not identified · pointer only |
| NucFuseRank: Dataset Fusion and Performance Ranking for Nuclei Instance Segmentation added by Syntology |
2026-01 (from id) |
masih4/NucleiAnalysis/datasets_stats.py 28a2dcba7477caee |
unverified |
MIT (permissive) |
| Typologically Informed Parameter Aggregation added by Syntology |
2026-01 (from id) |
stefaccou/TIPA/1_tipa_adapters.py 938ce6ad1ec1e4d3 |
unverified |
MIT (permissive) |
| MedRAGChecker: Claim-Level Verification for Biomedical Retrieval-Augmented Generation added by Syntology |
2026-01 (from id) |
JoyDajunSpaceCraft/MedicalRagChecker/DistillChecker/train_checker_grpo.py c31a4f29f9c5f375 |
unverified |
Apache-2.0 (permissive) |
| ImLoc: Revisiting Visual Localization with Image-based Representation added by Syntology |
2026-01 (from id) |
cvg/Hierarchical-Localization/hloc/extract_features.py 18761bb93ffb8441 |
unverified |
Apache-2.0 (permissive) |
| Linear Script Representations in Speech Foundation Models Enable Zero-Shot Transliteration added by Syntology |
2026-01 (from id) |
unicode-org/icu/icu4c/source/python/icutools/databuilder/__main__.py 264544e3e0f52aae |
unverified |
licence not identified · pointer only |
| Massive Editing for Large Language Models Based on Dynamic Weight Generation added by Syntology |
2025-12 (from id) |
RodeWayne/MeG-for-Knowledge-Editing/merge_results.py a5a29951e70ee65e |
unverified |
no licence file found · pointer only |
| RAG-IGBench: Innovative Evaluation for RAG-based Interleaved Generation in Open-domain Question Answering added by Syntology |
2025-12 (from id) |
USTC-StarTeam/RAG-IGBench/download_images.py 422100d6c65e4729 |
unverified |
Apache-2.0 (permissive) |
| Leak@k: Unlearning Does Not Make LLMs Forget Under Probabilistic Decoding added by Syntology |
2025-11 (from id) |
OptimAI-Lab/Leak-k/MUSE/RULE/training_muse/baselines/RULE.py 7cc7e7d9fb61ea51 |
unverified |
MIT (permissive) |
| Amortized Variational Inference for Partial-Label Learning: A Probabilistic Approach to Label Disambiguation added by Syntology |
2025-10 (from id) |
mathefuchs/vi-pll/vi_results.py 005695f982f5e386 |
unverified |
MIT (permissive) |
| QuadEnhancer: Leveraging Quadratic Transformations to Enhance Deep Neural Networks added by Syntology |
2025-10 (from id) |
chitar/QuadEnhancer/LLM-finetuning/commonsense_evaluate.py 415f46d8a341e28d |
unverified |
no licence file found · pointer only |
| QuadEnhancer: Leveraging Quadratic Transformations to Enhance Deep Neural Networks added by Syntology |
2025-10 (from id) |
chitar/QuadEnhancer/LLM-finetuning/evaluate.py 3398969fc7af6ff7 |
unverified |
no licence file found · pointer only |
| EMR-AGENT: Automating Cohort and Feature Extraction from EMR Databases added by Syntology |
2025-10 (from id) |
AITRICS/EMR-AGENT/EMR-Agent/featureMap_evaluation.py c358139bc207e774 |
unverified |
MIT (permissive) |
| Controlled Generation for Private Synthetic Text added by Syntology |
2025-09 (from id) |
zzhao71/Controlled-Generation-for-Private-Synthetic-Text/run_experiments.py c45aaaffcbb1a729 |
unverified |
no licence file found · pointer only |
| EdiVal-Agent: An Object-Centric Framework for Automated, Fine-Grained Evaluation of Multi-Turn Editing added by Syntology |
2025-09 (from id) |
TianyuCodings/EdiVal/baseline_generate/gpt4o.py f05a8bb234c77122 |
unverified |
no licence file found · pointer only |
| Model State Arithmetic for Machine Unlearning |
26 Jun 2025 |
mehrdadsaberi/msa_unlearning/src/tv_unlearn.py aa93c2f32ef7df6c |
unverified |
Apache-2.0 (permissive) |
| DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation |
25 Jun 2025 |
apple/ml-diffucoder/recipes/process_data.py f32a6b72ed50b5fa |
unverified |
licence not identified · pointer only |
| V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning |
11 Jun 2025 |
facebookresearch/vjepa2/app/scaffold.py 2004d0e6ae873f2e |
unverified |
MIT recorded; this copy not marked cleared · pointer only |
| Adversarial Paraphrasing: A Universal Attack for Humanizing AI-Generated Text |
8 Jun 2025 |
chengez/adversarial-paraphrasing/paraphrase_and_detect.py 0d612568417dbdae |
unverified |
Apache-2.0 (permissive) |
| Causal-LLaVA: Causal Disentanglement for Mitigating Hallucination in Multimodal Large Language Models |
26 May 2025 |
ignisavium/causal-llava/confounders/get_projector_confounders.py 4a7d0d350746fb32 |
unverified |
MIT (permissive) |
| STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings |
18 Apr 2025 |
codeboy5/stamp/src/rephrase_dataset.py 5d24c302b06c761b |
unverified |
Apache-2.0 (permissive) |
| Agentic Knowledgeable Self-awareness |
4 Apr 2025 |
zjunlp/knowself/train/train_stage1.py 5bbf3791e217df26 |
unverified |
MIT (permissive) |
| ESC: Erasing Space Concept for Knowledge Deletion |
3 Apr 2025 |
KU-VGI/ESC/unlearn.py a31522fb137cd85a |
unverified |
no licence file found · pointer only |
| arXiv:2502.21271 |
2025-02 (from id) |
ncTimTang/AKS/frame_select.py 7b2234adf426836f |
unverified |
no licence file found · pointer only |
| LongRoPE2: Near-Lossless LLM Context Window Scaling |
27 Feb 2025 |
microsoft/longrope/utils/tokenize_dataset.py 6db116407605786c |
unverified |
MIT (permissive) |
| FLEKE: Federated Locate-then-Edit Knowledge Editing |
21 Feb 2025 |
zongkaiz/fleke/FedEdit/summarize.py 4c92a4c8c2ffc80f |
unverified |
no licence file found · pointer only |
| AutoToM: Automated Bayesian Inverse Planning and Model Discovery for Open-ended Theory of Mind |
21 Feb 2025 |
chuanyangjin/MMToM-QA/BIP-ALM/inverse_symbolic_planner.py 15217c48be12b1ec |
unverified |
Apache-2.0 (permissive) |
| Proving Olympiad Inequalities by Synergizing LLMs and Symbolic Reasoning |
19 Feb 2025 |
Lizn-zn/NeqLIPS/viz.py ec2913a87bc45c5c |
unverified |
MIT (permissive) |
| Train Small, Infer Large: Memory-Efficient LoRA Training for Large Language Models |
19 Feb 2025 |
junzhang-zj/LoRAM/loram/2_pruned_low_rank_matrix_training.py 1382890bcd6d3bc9 |
unverified |
Apache-2.0 (permissive) |
| Primus: A Pioneering Collection of Open-Source Datasets for Cybersecurity LLM Training |
16 Feb 2025 |
huggingface/cosmopedia/classification/run_edu_bert.py 6d7f9ea09392e2a8 |
unverified |
Apache-2.0 (permissive) |
| AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Society |
12 Feb 2025 |
tsinghua-fib-lab/AgentSociety/extension/runtime/agentsociety/bin/ags.py 90fa4d60b1313975 |
unverified |
Apache-2.0 (permissive) |
| arXiv:2502.03397 |
2025-02 (from id) |
honglizhan/SPRI-public/stage1_gen_principles/02_refine_principles.py cc3134c9d977d49c |
unverified |
no licence file found · pointer only |
| SPRec: Leveraging Self-Play to Debias Preference Alignment for Large Language Model-based Recommendations |
12 Dec 2024 |
regionch/sprec/eval/inference.py 42ea65e48852f658 |
unverified |
no licence file found · pointer only |
| SPRec: Leveraging Self-Play to Debias Preference Alignment for Large Language Model-based Recommendations |
12 Dec 2024 |
regionch/sprec/train/data_generate.py 0b117d807444bd80 |
unverified |
no licence file found · pointer only |
| TSD-SR: One-Step Diffusion with Target Score Distillation for Real-World Image Super-Resolution |
27 Nov 2024 |
Microtreei/TSD-SR/test/test_tsdsr.py ef8e881c60cb2521 |
unverified |
Apache-2.0 (permissive) |
| Probing the limitations of multimodal language models for chemistry and materials research |
25 Nov 2024 |
lamalab-org/mac-bench/plots/table_models.py a3db863da80a39c5 |
unverified |
MIT (permissive) |
| Robust and Efficient Fine-tuning of LLMs with Bayesian Reparameterization of Low-Rank Adaptation |
7 Nov 2024 |
lcs2-iiitd/monteclora/commonsense_evaluate.py 93ae876f7bcc5547 |
unverified |
Apache-2.0 (permissive) |
| Robust and Efficient Fine-tuning of LLMs with Bayesian Reparameterization of Low-Rank Adaptation |
7 Nov 2024 |
lcs2-iiitd/monteclora/evaluate.py 2982bc8c318ebd42 |
unverified |
Apache-2.0 (permissive) |
| Benchmarking Vision Language Model Unlearning via Fictitious Facial Identity Dataset |
5 Nov 2024 |
safolab-wisc/fiubench/aggregate_eval_stat.py 1090886208057542 |
unverified |
no licence file found · pointer only |
| Quantifying Aleatoric Uncertainty of the Treatment Effect: A Novel Orthogonal Learner |
5 Nov 2024 |
valentyn1997/au-cnfs/runnables/train_lockdown.py 5b354bae6f4dff6f |
unverified |
no licence file found · pointer only |
| Right this way: Can VLMs Guide Us to See More to Answer Questions? |
1 Nov 2024 |
LeoLee7/Directional_guidance/generate_train_dataset_main.py 2ca535421a0f566a |
unverified |
MIT (permissive) |
| SelfCodeAlign: Self-Alignment for Code Generation |
31 Oct 2024 |
bigcode-project/selfcodealign/src/star_align/self_ossinstruct.py 5c02c0de38a6ae98 |
unverified |
Apache-2.0 (permissive) |
| Read-ME: Refactorizing LLMs as Router-Decoupled Mixture of Experts with System Co-Design |
24 Oct 2024 |
VITA-Group/READ-ME/moe_fication/train_red.py 01f915e04e3d24d0 |
unverified |
no licence file found · pointer only |
| Scalable Data Ablation Approximations for Language Models through Modular Training and Merging |
21 Oct 2024 |
clarana/ez-data-ablations/save_uniform_avg_model.py feda6cc4a9b1ac61 |
unverified |
Apache-2.0 (permissive) |
| Modeling Future Conversation Turns to Teach LLMs to Ask Clarifying Questions |
17 Oct 2024 |
mikejqzhang/clarifying_questions/src/clarifying_rewards.py 5516bbeb1337ab04 |
unverified |
no licence file found · pointer only |
| CollabEdit: Towards Non-destructive Collaborative Knowledge Editing |
12 Oct 2024 |
lins-lab/collabedit/experiments/CollabEdit_summarize.py 3da2cb78951884b7 |
unverified |
MIT (permissive) |
| MTL-LoRA: Low-Rank Adaptation for Multi-Task Learning |
12 Oct 2024 |
pumpkin-co/mtl-lora/lora_evaluate.py 9b2aa09fa1644193 |
unverified |
MIT (permissive) |
| Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models |
10 Oct 2024 |
kbsdjames/omni-math/Omni-Judge_eval/detailed_evaluation/difficulty_specific_evaluation.py a2095803e48965a1 |
unverified |
no licence file found · pointer only |
| Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models |
10 Oct 2024 |
kbsdjames/omni-math/GPT_eval/detailed_evaluation/difficulty_specific_evaluation.py b7f72b95c867a1ec |
unverified |
no licence file found · pointer only |
| Efficient Inference for Large Language Model-based Generative Recommendation |
7 Oct 2024 |
Linxyhaha/AtSpeed/code/generate_teacher_data.py e2f64861d2469ffb |
unverified |
no licence file found · pointer only |
| CS4: Measuring the Creativity of Large Language Models Automatically by Controlling the Number of Story-Writing Constraints |
5 Oct 2024 |
anirudhlakkaraju/cs4_benchmark/evaluation/constraint_satisfaction.py 1a773a549f580915 |
unverified |
MIT (permissive) |
| CS4: Measuring the Creativity of Large Language Models Automatically by Controlling the Number of Story-Writing Constraints |
5 Oct 2024 |
anirudhlakkaraju/cs4_benchmark/evaluation/diversity_calculation.py 5baffd5407078613 |
unverified |
MIT (permissive) |
| CS4: Measuring the Creativity of Large Language Models Automatically by Controlling the Number of Story-Writing Constraints |
5 Oct 2024 |
anirudhlakkaraju/cs4_benchmark/evaluation/diversity_graphs.py c811600eab5c3bf7 |
unverified |
MIT (permissive) |
| Hyperbolic Fine-tuning for Large Language Models |
5 Oct 2024 |
marlin-codes/HypLLM/commonsense_evaluate_gemma.py 27ce6e249f9b1a82 |
unverified |
no licence file found · pointer only |
| Hyperbolic Fine-tuning for Large Language Models |
5 Oct 2024 |
marlin-codes/HypLLM/commonsense_evaluate_qwen.py e563b8e4282a0c32 |
unverified |
no licence file found · pointer only |
| Hyperbolic Fine-tuning for Large Language Models |
5 Oct 2024 |
marlin-codes/HypLLM/evaluate.py 11971b0db65e9e75 |
unverified |
no licence file found · pointer only |
| Dataset Distillation via Knowledge Distillation: Towards Efficient Self-Supervised Pre-Training of Deep Networks |
3 Oct 2024 |
bigml-cs-ucla/mkdt/distill.py 6e3eefbc9e2d6162 |
unverified |
no licence file found · pointer only |
| MEOW: MEMOry Supervised LLM Unlearning Via Inverted Facts |
18 Sep 2024 |
carol-gutianle/meow/meow/tofu/aggregate.py 956672833b0ef856 |
ran
|
no licence file found · pointer only |
| Train Till You Drop: Towards Stable and Robust Source-free Unsupervised 3D Domain Adaptation |
6 Sep 2024 |
valeoai/TTYD/train_ttyd_st.py 14efea405afb2bd4 |
unverified |
no licence file found · pointer only |
| Train Till You Drop: Towards Stable and Robust Source-free Unsupervised 3D Domain Adaptation |
6 Sep 2024 |
valeoai/ttyd/train_ttyd_core.py b8410a4af7b88726 |
unverified |
no licence file found · pointer only |
| Task-Specific Directions: Definition, Exploration, and Utilization in Parameter Efficient Fine-Tuning |
2 Sep 2024 |
Chongjie-Si/Subspace-Tuning/CR_MR/commonsense_evaluate.py 415f46d8a341e28d |
unverified |
Apache-2.0 (permissive) |
| Task-Specific Directions: Definition, Exploration, and Utilization in Parameter Efficient Fine-Tuning |
2 Sep 2024 |
Chongjie-Si/Subspace-Tuning/CR_MR/math_evaluate.py 4740c3e235eedfb4 |
unverified |
Apache-2.0 (permissive) |
| Segment Any Mesh: Zero-shot Mesh Part Segmentation via Lifting Segment Anything 2 to 3D |
24 Aug 2024 |
gtangg12/samesh/src/samesh/__main__.py 59cc1ae133a0c105 |
unverified |
no licence file found · pointer only |
| Self-Explainable Graph Transformer for Link Sign Prediction |
16 Aug 2024 |
liule66/SE-SGformer/discriminator.py 2de872249d4741db |
unverified |
no licence file found · pointer only |
| SCOI: Syntax-augmented Coverage-based In-context Example Selection for Machine Translation |
9 Aug 2024 |
hplt-project/sacremoses/audit/differential.py c6fe46bed16bd015 |
unverified |
MIT (permissive) |
| Revisiting Who's Harry Potter: Towards Targeted Unlearning from a Causal Intervention Perspective |
24 Jul 2024 |
ucsb-nlp-chang/causal_unlearn/aggregate_eval_tofu.py 060156a110cfcc2e |
unverified |
MIT (permissive) |
| Preventing Catastrophic Overfitting in Fast Adversarial Training: A Bi-level Optimization Perspective |
17 Jul 2024 |
HandingWangXDGroup/FGSM-PCO/FGSM-PCO.py 9bf5d16916540519 |
unverified |
no licence file found · pointer only |