| Option-Aware Retrieval and Task-Specific VLM Adaptation for Medical VQA added by Syntology |
2026-09 (from id) |
Kirscher/MedReason2026/finetune/train_lora_qwen25vl.py 07f007e3a1985c92 |
unverified |
Apache-2.0 (permissive) |
| LEARNING CONTINUOUS SOURCE RESPONSES FOR GENERALIZABLE AI-GENERATED IMAGE DETECTION added by Syntology |
2026-09 (from id) |
manic-cui/CuRe/cure/model.py b02a1d9300960243 |
unverified |
Apache-2.0 (permissive) |
| One Size Does Not Fit All Setting Inference Depth from the Questions a Deployment Actually Asks added by Syntology |
2026-09 (from id) |
jerrykaplan/question-conditioned-early-exit/code/pipeline.py afc32ea86d30bc31 |
unverified |
MIT (permissive) |
| S$^2$Prune: Spatially Structured Visual Token Pruning for Multimodal Large Language Models added by Syntology |
2026-09 (from id) |
yuanyuanjia71-spec/S2Prune/s2prune/qwen.py 8cbe1d5962ac9dab |
unverified |
no licence file found · pointer only |
| A Glance Is All You Need: Single-Pass Fine-Grained Image Captioning with SimLoss added by Syntology |
2026-09 (from id) |
srynsh/SimLoss-Image-Captioning/simloss/grpo_gemini/eval_checkpoint.py 3010b88e4be192d4 |
unverified |
no licence file found · pointer only |
| Stress-Testing Efficient Responsible-AI Evaluation: When Compute Savings Change Benchmark Conclusions added by Syntology |
2026-08 (from id) |
VectorInstitute/sustainable-rai-evaluation/src/evaluation_has_a_footprint/inference.py ac797b8a96bcf2ca |
unverified |
Apache-2.0 (permissive) |
| The Dialect Tax: Dialectal Biases Persist throughout the Language Modeling Pipeline added by Syntology |
2026-08 (from id) |
socialnlp/dialecttax/src/dialecttax/gradients.py c562479f4ac54069 |
unverified |
MIT (permissive) |
| The Dialect Tax: Dialectal Biases Persist throughout the Language Modeling Pipeline added by Syntology |
2026-08 (from id) |
socialnlp/dialecttax/src/dialecttax/layers.py ec1366915e828453 |
unverified |
MIT (permissive) |
| The Geometry of Low-Resource Language Representations added by Syntology |
2026-08 (from id) |
francois-meyer/cpt-geometry/compute_geometric_metrics.py 6e5e67d5fee802c9 |
unverified |
no licence file found · pointer only |
| ClosureBench: Compositional Graph Reasoning ClosureBench: A Constructive Benchmark for Compositional Graph Reasoning added by Syntology |
2026-08 (from id) |
egolabs-ai/closurebench/src/closurebench/model_runner.py 2e42dd549759b1b3 |
unverified |
MIT (permissive) |
| BOCoDe: Engineering-Centered Benchmarking for Bayesian Optimization added by Syntology |
2026-08 (from id) |
XZT008/Standard-GP-is-all-you-need-for-HDBO/benchmark/nn_pruning_utils.py 94bf24acd89a9223 |
unverified |
no licence file found · pointer only |
| LODESTAR: Robust Entropy-Based Answer Selection in Retrieval-Augmented Generation for Question Answering -- Directing Frozen-LLM Entropy with a Reinforcement-Learned Prompt Polarizer under Misleading Passages added by Syntology |
2026-08 (from id) |
zjysteven/mink-plus-plus/run_concat.py 4ab747637b9f94fd |
unverified |
MIT (permissive) |
| LODESTAR: Robust Entropy-Based Answer Selection in Retrieval-Augmented Generation for Question Answering -- Directing Frozen-LLM Entropy with a Reinforcement-Learned Prompt Polarizer under Misleading Passages added by Syntology |
2026-08 (from id) |
zjysteven/mink-plus-plus/run_neighbor.py 16dffe12946ec141 |
unverified |
MIT (permissive) |
| LODESTAR: Robust Entropy-Based Answer Selection in Retrieval-Augmented Generation for Question Answering -- Directing Frozen-LLM Entropy with a Reinforcement-Learned Prompt Polarizer under Misleading Passages added by Syntology |
2026-08 (from id) |
zjysteven/mink-plus-plus/run_ref.py d20c0c29841239c7 |
unverified |
MIT (permissive) |
| MuseCritic: Learning Multi-Aspect Song Rewards through Natural-Language Aesthetic Critiques added by Syntology |
2026-08 (from id) |
WuqnEl/MuseCritic/infer/infer.py 86f4dc3a1cb82f70 |
unverified |
no licence file found · pointer only |
| A Distributed Acoustic Sensing Dataset for Vessel Detection and Localization in Submarine Cable Protection added by Syntology |
2026-07 (from id) |
UAH-PSI/das-vessel-detection/models/baseline_xgb_regression_model.py fa4e0107672fee04 |
ran
|
GPL-3.0 (copyleft) · pointer only |
| Total Variation Distance Estimation in Autoregressive Models added by Syntology |
2026-07 (from id) |
XunZhiyang/llm-tv-estimation/experiments/tv_estimate.py 801eda14b08668a6 |
unverified |
MIT (permissive) |
| Circuit Discovery, Evaluation, and Application Toolkit for Mechanistic Interpretability added by Syntology |
2026-07 (from id) |
Lexsi-Labs/CircuitKIT/src/circuitkit/quick.py d493cdc4a900b3b5 |
unverified |
licence not identified · pointer only |
| Multi-Scale ViT Inference with Habitat-Fit Priors and kNN Retrieval for Multi-Species Plant Identification added by Syntology |
2026-07 (from id) |
dsgt-arc/plantclef-2026/user/murilo/src/plantclef/model.py bcb5e1827bc3fd86 |
unverified |
MIT (permissive) |
| Learning Where to Look: A Reinforcement Learning Framework for Robust Micro-Ultrasound Prostate Cancer Detection added by Syntology |
2026-06 (from id) |
DeepRCL/Prost-RL/prostnfound/generate_clinical_plots.py d90980e2dc9b0791 |
ran
|
no licence file found · pointer only |
| Learning Where to Look: A Reinforcement Learning Framework for Robust Micro-Ultrasound Prostate Cancer Detection added by Syntology |
2026-06 (from id) |
DeepRCL/Prost-RL/prostnfound/inference.py f06764c411a6d202 |
ran
|
no licence file found · pointer only |
| Learning at the Right Pace: Adaptive Data Scheduling Improves LLM Reinforcement Learning added by Syntology |
2026-06 (from id) |
Richard-zrx/ADS/src/model_utils.py 3ec62009af07711a |
ran
|
Apache-2.0 (permissive) |
| When AUC Misleads: Polarization-Aware Evaluation of Deepfake Detectors under Domain Shift added by Syntology |
2026-06 (from id) |
10Ring/LAA-Net/models/utils.py e59ae2c29ff112ff |
unverified |
licence not identified · pointer only |
| Prefilling-dLLM: Predictive Prefilling for Long-Context Inference in Diffusion Language Models added by Syntology |
2026-06 (from id) |
menik1126/Prefilling-dLLM/prefilling_dllm_eval/prefilling_model.py 7f95d887a0d400a5 |
unverified |
MIT (permissive) |
| ChessMimic: Per-Rating Transformer Models for Human Move, Clock, and Outcome Prediction in Online Blitz Chess added by Syntology |
2026-06 (from id) |
CSSLab/maia3/maia3/uci.py a92a6857d4a61de8 |
unverified |
AGPL-3.0 (copyleft) · pointer only |
| Hoeffding Concept Bottleneck Models with Applications to Overhead Images added by Syntology |
2026-06 (from id) |
ericenouen/cbdebug/pcbm/models/derma_models.py cfb5f5240ab7204c |
unverified |
MIT (permissive) |
| Human-Alignment, Calibration, and Activation Patterns in Large Language Model Uncertainty added by Syntology |
2026-05 (from id) |
KyleAMoore/LLM-UQ-Align-and-Calibrate/LinearProbing/ActivationGrabber.py 6012bb03063365be |
unverified |
MIT (permissive) |
| Why We Need Speech to Evaluate Speech Translation added by Syntology |
2026-05 (from id) |
MaikeZuefle/speechCOMET/speechcomet-eval/eval_utils.py 3fa3ad39c2c36c62 |
unverified |
Apache-2.0 (permissive) |
| Curriculum Learning for Safety Alignment added by Syntology |
2026-05 (from id) |
Sandeep5500/curriculum-learning-for-safety/src/interpretability/probe_safety.py 28a23205d560ec6c |
unverified |
no licence file found · pointer only |
| Hidden-State Privacy Has an Empty Middle added by Syntology |
2026-05 (from id) |
okezue/tcc-research/two_channel/compute_subspace.py 5148fb5c61d1921e |
ran
|
MIT (permissive) |
| The Model Parking Tax: Quantifying the Hidden Energy Cost of Always-On GPU Model Deployment added by Syntology |
2026-05 (from id) |
8bitai/gpu-parking-tax/experiments/model_validation.py 26577c1c91197f36 |
unverified |
no licence file found · pointer only |
| Why SGD is not Brownian Motion: A New Perspective on Stochastic Dynamics added by Syntology |
2026-05 (from id) |
brain-lab-research/SGDiffusion/src/datamodelopt/core/checkpointing.py 645eff8e04b31c3e |
ran
|
no licence file found · pointer only |
| CopT: Contrastive On-Policy Thinking with Continuous Spaces for General and Agentic Reasoning added by Syntology |
2026-05 (from id) |
shishirpatil/gorilla/gorilla/inference/gorilla_eval.py ba873c8d7fc8d9c3 |
unverified |
Apache-2.0 (permissive) |
| Benchmarking and Evolving Reason-Reflect-Rectify for Reflective Visual Generation added by Syntology |
2026-05 (from id) |
xiaomoguhz/R3-Bench/r3bench/models/qwen2_5vl.py 9ce1684c2b4e4437 |
unverified |
licence not identified · pointer only |
| Protection Is (Nearly) All You Need: Structural Protection Dominates Scoring in Globally Capped KV Eviction added by Syntology |
2026-05 (from id) |
gpgabriel25/KVCacheBoundaryProtection/src/counterfact_kv_eviction/jax_inference.py 7ce53772f6a98f99 |
unverified |
licence not identified · pointer only |
| Towards Resource-Efficient LLMs: End-to-End Energy Accounting of Distillation Pipelines added by Syntology |
2026-05 (from id) |
StellarLuminosity/Energy/distill_bench/pipelines/kd_eval.py 99c76a090a976891 |
unverified |
no licence file found · pointer only |
| MuonQ: Enhancing Low-Bit Muon Quantization via Directional Fidelity Optimization added by Syntology |
2026-05 (from id) |
YupengSu/MuonQ/src/model.py e8a2ded649151f29 |
unverified |
Apache-2.0 (permissive) |
| Unlearners Can Lie: Evaluating and Improving Honesty in LLM Unlearning added by Syntology |
2026-05 (from id) |
OPTML-Group/ReVa/src/train/reva/utils.py 7bdf184a0ba57b39 |
ran
|
no licence file found · pointer only |
| Continuous First, Discrete Later: VQ-VAEs Without Dimensional Collapse added by Syntology |
2026-05 (from id) |
xyz-zy/vqvae_latent_span_collapse/VQGAN/eval_val_std.py a8836f887cef4509 |
unverified |
MIT (permissive) |
| InfoChess: A Game of Adversarial Inference and a Laboratory for Quantifiable Information Control added by Syntology |
2026-04 (from id) |
murphyka/infochess/agents/hiding_belief_vismax_agent.py 4dac3e8f15d9c31a |
ran · our draft was wrong
|
MIT (permissive) |
| CausalDetox: Causal Head Selection and Intervention for Language Model Detoxification added by Syntology |
2026-04 (from id) |
unitaryai/detoxify/detoxify/detoxify.py 784c42a453ac5e68 |
unverified |
Apache-2.0 (permissive) |
| Latent Planning Emerges with Scale added by Syntology |
2026-04 (from id) |
hannamw/model-planning-public/animal_stories/evaluate_animal_stories.py 09fd84d63d8f2a44 |
unverified |
MIT (permissive) |
| Identity as Attractor: Geometric Evidence for Persistent Agent Architecture in LLM Activation Space added by Syntology |
2026-04 (from id) |
b102e/yar-attractor-experiment/ablation_experiment/extract_activations.py 6f87471a2e2a3504 |
unverified |
no licence file found · pointer only |
| Unified Deployment-Aware Evaluation of Open Reasoning Language Models added by Syntology |
2026-04 (from id) |
mkboch/UDAE/models/loader.py 6b7c1e512fe35435 |
unverified |
no licence file found · pointer only |
| On Neural Scaling Laws for Weather Emulation through Continual Training added by Syntology |
2026-03 (from id) |
ShashankSubramanian/neural-scaling-weather/models/helpers.py 6de4ed472a68af2e |
unverified |
licence not identified · pointer only |
| Hear Both Sides: Efficient Multi-Agent Debate via Diversity-Aware Message Retention added by Syntology |
2026-03 (from id) |
DA2I2-SLM/DAR/src/model/falcon.py 83f5d8fd4615419d |
unverified |
MIT (permissive) |
| Hear Both Sides: Efficient Multi-Agent Debate via Diversity-Aware Message Retention added by Syntology |
2026-03 (from id) |
DA2I2-SLM/DAR/src/model/llama.py f8d90d67f4aad3ad |
unverified |
MIT (permissive) |
| Kimodo: Scaling Controllable Human Motion Generation added by Syntology |
2026-03 (from id) |
nv-tlabs/kimodo/kimodo/model/load_model.py 9864a44c22701ca7 |
unverified |
Apache-2.0 (permissive) |
| ZOTTA: Test-Time Adaptation with Gradient-Free Zeroth-Order Optimization added by Syntology |
2026-03 (from id) |
Zhang-Ronghao/zotta/tta_library/zotta.py 7b969394a74a96c4 |
unverified |
MIT (permissive) |
| UVLM: A Universal Vision-Language Model Loader for Reproducible Multimodal Benchmarking added by Syntology |
2026-03 (from id) |
perezjoan/UVLM/uvlm/loader.py 0ac9db5392bf70d0 |
unverified |
Apache-2.0 (permissive) |
| Meta-Reinforcement Learning with Self-Reflection for Agentic Search added by Syntology |
2026-03 (from id) |
tengxiao1/MR-Search/meta-search/search/index_builder.py 4260fe0918ac5196 |
unverified |
no licence file found · pointer only |
| Bound Propagation meets Constraint Simplification: Improving Logic-based XAI for Neural Networks added by Syntology |
2026-03 (from id) |
ronaldogomes96/explication-ann/src/models/utils.py 5fd51d1a8831f916 |
unverified |
no licence file found · pointer only |
| RETLLM: Training and Data-Free MLLMs for Multimodal Information Retrieval added by Syntology |
2026-02 (from id) |
alivecat05/RETLLM/main_eval.py 3e4ea555a8a80225 |
unverified |
Apache-2.0 (permissive) |
| Alternating Bi-Objective Optimization for Explainable Neuro-Fuzzy Systems added by Syntology |
2026-02 (from id) |
QusaiKhaled/XANFIS/visualizer.py 2387b8a3f0a8bbce |
unverified |
no licence file found · pointer only |
| Differences in Typological Alignment in Language Models' Treatment of Differential Argument Marking added by Syntology |
2026-02 (from id) |
Iskar-Deng/DAM-learning/evaluation/eval_minpairs_acc.py 0af832420874c823 |
unverified |
no licence file found · pointer only |
| OmniSapiens: A Foundation Model for Social Behavior Processing via Heterogeneity-Aware Relative Policy Optimization added by Syntology |
2026-02 (from id) |
MIT-MI/human_behavior_atlas/training/sft/train_sft.py 7380e01e3cd064c2 |
unverified |
no licence file found · pointer only |
| DUET: Distilled LLM Unlearning from an Efficiently Contextualized Teacher added by Syntology |
2026-01 (from id) |
EasonZhong99/DUET/eval_mmlu.py fa11352c89b1d959 |
unverified |
no licence file found · pointer only |
| DUET: Distilled LLM Unlearning from an Efficiently Contextualized Teacher added by Syntology |
2026-01 (from id) |
EasonZhong99/DUET/eval_qa_rouge.py 43ca23f94d7ca39e |
unverified |
no licence file found · pointer only |
| GraphAllocBench: A Flexible Benchmark for Preference-Conditioned Multi-Objective Policy Learning added by Syntology |
2026-01 (from id) |
jzh001/GraphAllocBench/graphallocbench/evaluation/model_utils.py fde5af6e100cd769 |
unverified |
MIT (permissive) |
| Fixed Aggregation Features Can Rival GNNs added by Syntology |
2026-01 (from id) |
celrm/fixed-aggregation-features/logger.py d8e306910a720c14 |
unverified |
no licence file found · pointer only |
| Explainable Uncertainty Quantification for Wastewater Treatment Energy Prediction via Interval Type-2 Neuro-Fuzzy System added by Syntology |
2026-01 (from id) |
QusaiKhaled/XUQ/src/utils/persistence.py 0b239de6c32d9aae |
unverified |
no licence file found · pointer only |
| A CROSS-MODALITY VALIDATION OF MRI VERSUS X-RAY added by Syntology |
2026-01 (from id) |
Malga-Vision/Landmarks-Hip-Conditions/deep_learning.py 4675b09039b1e3f2 |
unverified |
MIT (permissive) |
| UPLiFT: Efficient Pixel-Dense Feature Upsampling with Local Attenders added by Syntology |
2026-01 (from id) |
mwalmer-umd/UPLiFT/uplift/hub_loader.py 80db0b2e7f2f1d55 |
unverified |
MIT (permissive) |
| Reasoning Beyond Literal: Cross-style Multimodal Reasoning for Figurative Language Understanding added by Syntology |
2026-01 (from id) |
scheshmi/CrossStyle-MMR/infer/binary.py 59edd20c4877c02d |
unverified |
no licence file found · pointer only |
| Reasoning Beyond Literal: Cross-style Multimodal Reasoning for Figurative Language Understanding added by Syntology |
2026-01 (from id) |
scheshmi/CrossStyle-MMR/infer/deepseek.py 3c8e93cd926f0c75 |
unverified |
no licence file found · pointer only |
| Reasoning Beyond Literal: Cross-style Multimodal Reasoning for Figurative Language Understanding added by Syntology |
2026-01 (from id) |
scheshmi/CrossStyle-MMR/infer/sft_cot.py e6b5634816c6b7c0 |
unverified |
no licence file found · pointer only |
| Sycophancy Hides Linearly in the Attention Heads added by Syntology |
2026-01 (from id) |
rifoagenadi/sycophancy/utils.py 04576b9fbc4350fb |
unverified |
no licence file found · pointer only |
| Sycophancy Hides Linearly in the Attention Heads added by Syntology |
2026-01 (from id) |
rifoagenadi/sycophancy/extension/extract_activations.py c5c3f8ddf9c8f027 |
unverified |
no licence file found · pointer only |
| Domain-Specific Knowledge Graphs in RAG-Enhanced Healthcare LLMs added by Syntology |
2026-01 (from id) |
sydneyanuyah/RAGComparison/artifacts/complex_simplify_sentences.py f242630adcccd143 |
unverified |
no licence file found · pointer only |
| Language-Coupled Reinforcement Learning for Multilingual Retrieval-Augmented Generation added by Syntology |
2026-01 (from id) |
Cherry-qwq/LcRL-Open/search_r1/search/index_builder.py 4260fe0918ac5196 |
unverified |
Apache-2.0 (permissive) |
| EmoLat: Text-driven Image Sentiment Transfer via Emotion Latent Space added by Syntology |
2026-01 (from id) |
JingVIPLab/EmoLat/emo_token_gen_model/emo_token_gen_model.py 052d17d995e09058 |
unverified |
no licence file found · pointer only |
| MatchTIR: Fine-Grained Supervision for Tool-Integrated Reasoning via Bipartite Matching added by Syntology |
2026-01 (from id) |
bytedance/FTRL/Code/utils/utils.py ec450fb84a121b33 |
unverified |
Apache-2.0 (permissive) |
| Evaluating the Diagnostic Classification Ability of Multimodal Large Language Models: Insights from the Osteoarthritis Initiative added by Syntology |
2026-01 (from id) |
wanglihx/LLaVA-OA/3-clip/clipeval.py a7a6d2fd4d5b010b |
unverified |
no licence file found · pointer only |
| HalluZig: Hallucination Detection using Zigzag Persistence added by Syntology |
2026-01 (from id) |
TDA-Jyamiti/halluzig/utils.py b09843d4d3ac9742 |
unverified |
no licence file found · 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/myDataloader_bert_text_add_nq_lr.py 5f81834e47a60a64 |
unverified |
no licence file found · 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/myDataloader_cf_bert_text_add_nq_lr.py 4a80e760cc60c9b9 |
unverified |
no licence file found · pointer only |
| Evaluating Foundation Models' 3D Understanding Through Multi-View Correspondence Analysis added by Syntology |
2025-12 (from id) |
ToyeshC/open-hummingbird-3d-eval/python_scripts/run_eval_4_table_reproduction.py 376edd4d5015083b |
unverified |
MIT (permissive) |
| Evaluating Foundation Models' 3D Understanding Through Multi-View Correspondence Analysis added by Syntology |
2025-12 (from id) |
ToyeshC/open-hummingbird-3d-eval/python_scripts/old_exp_b.py 0b0243bb299195f2 |
unverified |
MIT (permissive) |
| Open Polymer Challenge: Post-Competition Report added by Syntology |
2025-12 (from id) |
sobinalosious/ADEPT/3.Analysis/predict_tg.py dd3d61d82c74d5f1 |
unverified |
no licence file found · pointer only |
| Unifying and Enhancing Graph Transformers via a Hierarchical Mask Framework added by Syntology |
2025-10 (from id) |
null-xyj/M3Dphormer/logger.py 36604764af0f2cb1 |
unverified |
no licence file found · pointer only |
| Quantifying Climate Policy Action and Its Links to Development Outcomes: A Cross-National Data-Driven Analysis added by Syntology |
2025-10 (from id) |
booktrackerGirl/climate_change_policy_analysis/src/summarizer_script.py 77abb22b27773143 |
unverified |
MIT (permissive) |
| Fly-CL: A Fly-Inspired Framework for Enhancing Efficient Decorrelation and Reduced Training Time in Pre-trained Model-based Continual Representation Learning added by Syntology |
2025-10 (from id) |
gfyddha/Fly-CL/models/load_model.py 33865bb75490b774 |
unverified |
MIT (permissive) |
| ESCA: Contextualizing Embodied Agents via Scene-Graph Generation added by Syntology |
2025-10 (from id) |
video-fm/ESCA/embodiedbench/planner/navigation/esca.py d4e8a6e34592c45a |
unverified |
no licence file found · pointer only |
| Domain-Shift-Aware Conformal Prediction for Large Language Models added by Syntology |
2025-10 (from id) |
smartyfh/LLM-Uncertainty-Bench/generate_logits.py 35ff91b4ff9b46ab |
unverified |
MIT (permissive) |
| Domain-Shift-Aware Conformal Prediction for Large Language Models added by Syntology |
2025-10 (from id) |
smartyfh/LLM-Uncertainty-Bench/generate_logits_chat.py ba6a8351d724ca74 |
unverified |
MIT (permissive) |
| Retrieval-Augmented Generation for Reliable Interpretation of Radio Regulations added by Syntology |
2025-09 (from id) |
Zakaria010/Radio-RAG/local_rag.py 6f60f347c4394a7a |
unverified |
MIT (permissive) |
| Debate or Vote: Which Yields Better Decisions in Multi-Agent Large Language Models? added by Syntology |
2025-08 (from id) |
deeplearning-wisc/debate-or-vote/src/model/llama.py d37a4d52cbb58ff4 |
unverified |
no licence file found · pointer only |
| Debate or Vote: Which Yields Better Decisions in Multi-Agent Large Language Models? added by Syntology |
2025-08 (from id) |
deeplearning-wisc/debate-or-vote/src/model/qwen.py 5eac478ca93897a7 |
unverified |
no licence file found · pointer only |
| Adversarial Manipulation of Reasoning Models using Internal Representations |
3 Jul 2025 |
ky295/reasoning-manipulation/interventions/create_ortho_model.py d4f29e94e48d679d |
unverified |
MIT (permissive) |
| Adversarial Manipulation of Reasoning Models using Internal Representations |
3 Jul 2025 |
ky295/reasoning-manipulation/interventions/activation_addition.py 2410d0fa9fb4d711 |
unverified |
MIT (permissive) |
| Model State Arithmetic for Machine Unlearning |
26 Jun 2025 |
mehrdadsaberi/msa_unlearning/src/tv_unlearn.py fba3196222b060a3 |
unverified |
Apache-2.0 (permissive) |
| arXiv:2506.18434 |
2025-06 (from id) |
fruffini/PEFT_Prognosis/src/utils/save_load.py 83b037cd6a2822a5 |
unverified |
no licence file found · pointer only |
| Test3R: Learning to Reconstruct 3D at Test Time |
16 Jun 2025 |
nopqaq/test3r/dust3r/model.py 1e3f140b86bb9a08 |
unverified |
licence not identified · pointer only |
| KVzip: Query-Agnostic KV Cache Compression with Context Reconstruction |
29 May 2025 |
snu-mllab/kvzip/model/load.py 9c76a69893a315be |
unverified |
MIT (permissive) |
| ChatVLA-2: Vision-Language-Action Model with Open-World Embodied Reasoning from Pretrained Knowledge |
28 May 2025 |
tutujingyugang1/ChatVLA_public/qwen2_vla/model_load_utils.py e298c3ed316c8dcb |
unverified |
MIT (permissive) |
| InfoCons: Identifying Interpretable Critical Concepts in Point Clouds via Information Theory |
26 May 2025 |
llffff/infocons-pc/code/vis.py 6b2e031c74a89cd1 |
unverified |
no licence file found · pointer only |
| InfoCons: Identifying Interpretable Critical Concepts in Point Clouds via Information Theory |
26 May 2025 |
llffff/infocons-pc/code/test_dgcnn.py 918da5cdc787eff9 |
unverified |
no licence file found · pointer only |
| InfoCons: Identifying Interpretable Critical Concepts in Point Clouds via Information Theory |
26 May 2025 |
llffff/infocons-pc/code/test_curvenet.py ef4599d55ac1fe73 |
unverified |
no licence file found · pointer only |
| VisCRA: A Visual Chain Reasoning Attack for Jailbreaking Multimodal Large Language Models |
26 May 2025 |
DyMessi/VisCRA/qwenmask.py 317d970e6d4be3bc |
unverified |
Apache-2.0 (permissive) |
| Moonbeam: A MIDI Foundation Model Using Both Absolute and Relative Music Attributes |
21 May 2025 |
guozixunnicolas/Moonbeam-MIDI-Foundation-Model/src/llama_recipes/inference/model_utils.py 6533a38ad979d2b6 |
unverified |
Apache-2.0 (permissive) |
| Better Safe Than Sorry? Overreaction Problem of Vision Language Models in Visual Emergency Recognition |
21 May 2025 |
Dasol-Choi/VERI-Emergency/src/q1_evaluation.py 55325907ea1100df |
unverified |
MIT (permissive) |
| OpenHelix: A Short Survey, Empirical Analysis, and Open-Source Dual-System VLA Model for Robotic Manipulation |
6 May 2025 |
OpenHelix-robot/OpenHelix/data_preprocessing/preprocess_calvin_instructions.py 1eb3169facaa8376 |
unverified |
MIT (permissive) |
| Zero-Shot Whole-Body Humanoid Control via Behavioral Foundation Models |
15 Apr 2025 |
facebookresearch/metamotivo/metamotivo/fb/model.py feddcd5c2a9fd9a2 |
ran · our draft was wrong
|
licence not identified · pointer only |
| Less-to-More Generalization: Unlocking More Controllability by In-Context Generation |
2 Apr 2025 |
bytedance/UNO/uno/flux/pipeline.py 5317947c40cdbb83 |
ran
|
Apache-2.0 (permissive) |
| EgoToM: Benchmarking Theory of Mind Reasoning from Egocentric Videos |
28 Mar 2025 |
facebookresearch/egotom/code/vlm_evaluate.py 30a7dbbd7f93015f |
unverified |
licence not identified · pointer only |
| CaKE: Circuit-aware Editing Enables Generalizable Knowledge Learners |
20 Mar 2025 |
zjunlp/CaKE/Analysis/utils.py bb42f5ad478b4dbf |
unverified |
MIT (permissive) |
| Addressing Overprescribing Challenges: Fine-Tuning Large Language Models for Medication Recommendation Tasks |
5 Mar 2025 |
zzhustc2016/lamo/utils/model_utils.py d6dbc80a8beff531 |
unverified |
MIT (permissive) |
| Periodic Materials Generation using Text-Guided Joint Diffusion Model |
1 Mar 2025 |
kdmsit/TGDMat/csp_task/eval_utils.py 415e6a383e6ff70c |
unverified |
MIT (permissive) |
| Leveraging Pre-Trained Visual Transformers for Multi-Band Photometric Light Curve Classification |
2025-02 (from id) |
dnlmoreno/VT_Model_for_LightCurves_Classification/scripts/run_online.py ff0dc1588120ada4 |
ran · our draft was wrong
|
no licence file found · pointer only |
| Self-Training Elicits Concise Reasoning in Large Language Models |
27 Feb 2025 |
tergelmunkhbat/concise-reasoning/src/model.py ab895046a21a97a7 |
unverified |
MIT (permissive) |
| LongSafety: Evaluating Long-Context Safety of Large Language Models |
24 Feb 2025 |
thu-coai/LongSafety/src/gen_model_response.py 7f8345e3b106eff8 |
unverified |
MIT (permissive) |
| From Text to Space: Mapping Abstract Spatial Models in LLMs during a Grid-World Navigation Task |
23 Feb 2025 |
mneuronico/griw-world-spatial-orientation-task/experiments/fns.py 038dc68a58ff4bb6 |
unverified |
MIT (permissive) |
| If Attention Serves as a Cognitive Model of Human Memory Retrieval, What is the Plausible Memory Representation? |
17 Feb 2025 |
aistairc/rnng-pytorch/beam_search.py 1b066f480d7472db |
unverified |
MIT (permissive) |
| HealthGPT: A Medical Large Vision-Language Model for Unifying Comprehension and Generation via Heterogeneous Knowledge Adaptation |
14 Feb 2025 |
dcdmllm/healthgpt/HealthGPT-Pro/inference/utils.py 750616b8b0408b73 |
unverified |
Apache-2.0 (permissive) |
| JBShield: Defending Large Language Models from Jailbreak Attacks through Activated Concept Analysis and Manipulation |
2025-02 (from id) |
NISPLab/JBShield/utils.py dd7e600e3d341579 |
unverified |
MIT (permissive) |
| LANTERN++: Enhancing Relaxed Speculative Decoding with Static Tree Drafting for Visual Auto-regressive Models |
10 Feb 2025 |
jadohu/lantern/entrypoints/generate_images.py f52f760cc0bc6497 |
unverified |
no licence file found · pointer only |