{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/transformer/papers/39","list_of":"/method/transformer","method":"Transformer","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":39,"pages_in_order":140,"rows_per_page":100,"rows":[3801,3900],"of":13999,"counts":{"archive_papers_tagged":13999,"with_a_code_link":6572,"where_syntology_ran_a_sample":2248,"not_listed_spam_title":0,"listed":13999,"listed_where_code_ran":2248,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1919,"every_run_a_failure_of_syntologys_instrument":329,"listed_with_a_run_with_no_instrument_failure":1919,"listed_every_run_a_failure_of_syntologys_instrument":329,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/method/transformer","prev":"/method/transformer/papers/38","next":"/method/transformer/papers/40","papers":[{"paper":"/paper/jailbreakeval-an-integrated-toolkit-for","slug":"jailbreakeval-an-integrated-toolkit-for","title":"JailbreakEval: An Integrated Toolkit for Evaluating Jailbreak Attempts Against Large Language Models","date":"2024-06-13","arxiv_id":"2406.09321","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["thuccslab/jailbreakeval"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"linguistic-bias-in-chatgpt-language-models","title":"Linguistic Bias in ChatGPT: Language Models Reinforce Dialect Discrimination","date":"2024-06-13","arxiv_id":"2406.08818","n_code_links":0,"syntology":null},{"paper":null,"slug":"low-overhead-channel-estimation-via-3d","title":"Low-Overhead Channel Estimation via 3D Extrapolation for TDD mmWave Massive MIMO Systems Under High-Mobility Scenarios","date":"2024-06-13","arxiv_id":"2406.08887","n_code_links":0,"syntology":null},{"paper":null,"slug":"mgrq-post-training-quantization-for-vision","title":"MGRQ: Post-Training Quantization For Vision Transformer With Mixed Granularity Reconstruction","date":"2024-06-13","arxiv_id":"2406.09229","n_code_links":0,"syntology":null},{"paper":null,"slug":"omnih2o-universal-and-dexterous-human-to","title":"OmniH2O: Universal and Dexterous Human-to-Humanoid Whole-Body Teleoperation and Learning","date":"2024-06-13","arxiv_id":"2406.08858","n_code_links":0,"syntology":null},{"paper":"/paper/q-mamba-on-first-exploration-of-vision-mamba","slug":"q-mamba-on-first-exploration-of-vision-mamba","title":"QMamba: On First Exploration of Vision Mamba for Image Quality Assessment","date":"2024-06-13","arxiv_id":"2406.09546","n_code_links":1,"syntology":null},{"paper":null,"slug":"readctrl-personalizing-text-generation-with","title":"ReadCtrl: Personalizing text generation with readability-controlled instruction learning","date":"2024-06-13","arxiv_id":"2406.09205","n_code_links":0,"syntology":null},{"paper":null,"slug":"scoreformer-a-surrogate-model-for-large-scale","title":"Scoreformer: A Surrogate Model For Large-Scale Prediction of Docking Scores","date":"2024-06-13","arxiv_id":"2406.09346","n_code_links":0,"syntology":null},{"paper":null,"slug":"separations-in-the-representational","title":"Separations in the Representational Capabilities of Transformers and Recurrent Architectures","date":"2024-06-13","arxiv_id":"2406.09347","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformers-meet-neural-algorithmic","title":"Transformers meet Neural Algorithmic Reasoners","date":"2024-06-13","arxiv_id":"2406.09308","n_code_links":0,"syntology":null},{"paper":"/paper/vertical-lora-dense-expectation-maximization","slug":"vertical-lora-dense-expectation-maximization","title":"Vertical LoRA: Dense Expectation-Maximization Interpretation of Transformers","date":"2024-06-13","arxiv_id":"2406.09315","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-robust-pipeline-for-classification-and","title":"A Robust Pipeline for Classification and Detection of Bleeding Frames in Wireless Capsule Endoscopy using Swin Transformer and RT-DETR","date":"2024-06-12","arxiv_id":"2406.08046","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-sociotechnical-lens-for-evaluating-computer","title":"A Sociotechnical Lens for Evaluating Computer Vision Models: A Case Study on Detecting and Reasoning about Gender and Emotion","date":"2024-06-12","arxiv_id":"2406.08222","n_code_links":0,"syntology":null},{"paper":null,"slug":"adanca-neural-cellular-automata-as-adaptors","title":"AdaNCA: Neural Cellular Automata As Adaptors For More Robust Vision Transformer","date":"2024-06-12","arxiv_id":"2406.08298","n_code_links":0,"syntology":null},{"paper":"/paper/an-empirical-study-of-mamba-based-language","slug":"an-empirical-study-of-mamba-based-language","title":"An Empirical Study of Mamba-based Language Models","date":"2024-06-12","arxiv_id":"2406.07887","n_code_links":1,"syntology":null},{"paper":null,"slug":"automated-information-extraction-from-thyroid","title":"Automated Information Extraction from Thyroid Operation Narrative: A Comparative Study of GPT-4 and Fine-tuned KoELECTRA","date":"2024-06-12","arxiv_id":"2406.07922","n_code_links":0,"syntology":null},{"paper":"/paper/bilateral-interaction-for-local-global","slug":"bilateral-interaction-for-local-global","title":"Bilateral Interaction for Local-Global Collaborative Perception in Low-Light Image Enhancement","date":"2024-06-12","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"cldta-contrastive-learning-based-on-diagonal","title":"CLDTA: Contrastive Learning based on Diagonal Transformer Autoencoder for Cross-Dataset EEG Emotion Recognition","date":"2024-06-12","arxiv_id":"2406.08081","n_code_links":0,"syntology":null},{"paper":"/paper/concepthash-interpretable-fine-grained","slug":"concepthash-interpretable-fine-grained","title":"ConceptHash: Interpretable Fine-Grained Hashing via Concept Discovery","date":"2024-06-12","arxiv_id":"2406.08457","n_code_links":1,"syntology":null},{"paper":"/paper/ct3d-improving-3d-object-detection-with","slug":"ct3d-improving-3d-object-detection-with","title":"CT3D++: Improving 3D Object Detection with Keypoint-induced Channel-wise Transformer","date":"2024-06-12","arxiv_id":"2406.08152","n_code_links":1,"syntology":null},{"paper":"/paper/dafnybench-a-benchmark-for-formal-software","slug":"dafnybench-a-benchmark-for-formal-software","title":"DafnyBench: A Benchmark for Formal Software Verification","date":"2024-06-12","arxiv_id":"2406.08467","n_code_links":1,"syntology":null},{"paper":"/paper/fully-few-shot-class-incremental-audio","slug":"fully-few-shot-class-incremental-audio","title":"Fully Few-shot Class-incremental Audio Classification Using Expandable Dual-embedding Extractor","date":"2024-06-12","arxiv_id":"2406.08122","n_code_links":1,"syntology":null},{"paper":"/paper/helpsteer2-open-source-dataset-for-training","slug":"helpsteer2-open-source-dataset-for-training","title":"HelpSteer2: Open-source dataset for training top-performing reward models","date":"2024-06-12","arxiv_id":"2406.08673","n_code_links":1,"syntology":null},{"paper":null,"slug":"how-well-it-works-benchmarking-performance-of","title":"How well it works: Benchmarking performance of GPT models on medical natural language processing tasks","date":"2024-06-12","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"i-don-t-know-you-but-i-can-catch-you-real","title":"I Don't Know You, But I Can Catch You: Real-Time Defense against Diverse Adversarial Patches for Object Detectors","date":"2024-06-12","arxiv_id":"2406.10285","n_code_links":0,"syntology":null},{"paper":"/paper/indirectrequests-making-task-oriented","slug":"indirectrequests-making-task-oriented","title":"Making Task-Oriented Dialogue Datasets More Natural by Synthetically Generating Indirect User Requests","date":"2024-06-12","arxiv_id":"2406.07794","n_code_links":0,"syntology":null},{"paper":"/paper/judging-the-judges-a-systematic-investigation","slug":"judging-the-judges-a-systematic-investigation","title":"Judging the Judges: A Systematic Study of Position Bias in LLM-as-a-Judge","date":"2024-06-12","arxiv_id":"2406.07791","n_code_links":1,"syntology":{"ran":16,"of":16,"n_ran_checked":16,"n_instrument":0,"unverified":0,"pointer_only":16,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["Slimshilin/Position-Bias-Analyzer-Demo"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":16,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/mail-improving-imitation-learning-with-mamba","slug":"mail-improving-imitation-learning-with-mamba","title":"MaIL: Improving Imitation Learning with Mamba","date":"2024-06-12","arxiv_id":"2406.08234","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["alrhub/mail"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"mistral-c2f-coarse-to-fine-actor-for","title":"Mistral-C2F: Coarse to Fine Actor for Analytical and Reasoning Enhancement in RLHF and Effective-Merged LLMs","date":"2024-06-12","arxiv_id":"2406.08657","n_code_links":0,"syntology":null},{"paper":null,"slug":"multimodal-representation-loss-between-timed","title":"Multimodal Representation Loss Between Timed Text and Audio for Regularized Speech Separation","date":"2024-06-12","arxiv_id":"2406.08328","n_code_links":0,"syntology":null},{"paper":"/paper/on-evaluating-adversarial-robustness-of","slug":"on-evaluating-adversarial-robustness-of","title":"On Evaluating Adversarial Robustness of Volumetric Medical Segmentation Models","date":"2024-06-12","arxiv_id":"2406.08486","n_code_links":1,"syntology":null},{"paper":"/paper/scaling-manipulation-learning-with-visual","slug":"scaling-manipulation-learning-with-visual","title":"Scaling Manipulation Learning with Visual Kinematic Chain Prediction","date":"2024-06-12","arxiv_id":"2406.07837","n_code_links":1,"syntology":null},{"paper":null,"slug":"supportiveness-based-knowledge-rewriting-for","title":"Supportiveness-based Knowledge Rewriting for Retrieval-augmented Language Modeling","date":"2024-06-12","arxiv_id":"2406.08116","n_code_links":0,"syntology":null},{"paper":"/paper/tailoring-generative-ai-chatbots-for","slug":"tailoring-generative-ai-chatbots-for","title":"Tailoring Generative AI Chatbots for Multiethnic Communities in Disaster Preparedness Communication: Extending the CASA Paradigm","date":"2024-06-12","arxiv_id":"2406.08411","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-importance-of-positional-encoding","title":"Learning positional encodings in transformers depends on initialization","date":"2024-06-12","arxiv_id":"2406.08272","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer-based-model-for-asr-n-best","title":"Transformer-based Model for ASR N-Best Rescoring and Rewriting","date":"2024-06-12","arxiv_id":"2406.08207","n_code_links":0,"syntology":null},{"paper":null,"slug":"veract-scan-retrieval-augmented-fake-news","title":"VeraCT Scan: Retrieval-Augmented Fake News Detection with Justifiable Reasoning","date":"2024-06-12","arxiv_id":"2406.10289","n_code_links":0,"syntology":null},{"paper":"/paper/what-if-we-recaption-billions-of-web-images","slug":"what-if-we-recaption-billions-of-web-images","title":"What If We Recaption Billions of Web Images with LLaMA-3?","date":"2024-06-12","arxiv_id":"2406.08478","n_code_links":0,"syntology":null},{"paper":"/paper/agent-simt-agent-assisted-simultaneous","slug":"agent-simt-agent-assisted-simultaneous","title":"Agent-SiMT: Agent-assisted Simultaneous Machine Translation with Large Language Models","date":"2024-06-11","arxiv_id":"2406.06910","n_code_links":1,"syntology":null},{"paper":"/paper/ai-sandbagging-language-models-can","slug":"ai-sandbagging-language-models-can","title":"AI Sandbagging: Language Models can Strategically Underperform on Evaluations","date":"2024-06-11","arxiv_id":"2406.07358","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["teunvdweij/sandbagging"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"beyond-words-on-large-language-models","title":"Beyond Words: On Large Language Models Actionability in Mission-Critical Risk Analysis","date":"2024-06-11","arxiv_id":"2406.10273","n_code_links":0,"syntology":null},{"paper":"/paper/dara-decomposition-alignment-reasoning","slug":"dara-decomposition-alignment-reasoning","title":"DARA: Decomposition-Alignment-Reasoning Autonomous Language Agent for Question Answering over Knowledge Graphs","date":"2024-06-11","arxiv_id":"2406.07080","n_code_links":1,"syntology":{"ran":9,"of":9,"n_ran_checked":9,"n_instrument":0,"unverified":0,"pointer_only":9,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["UKPLab/acl2024-DARA"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/entropy-reinforced-planning-with-large","slug":"entropy-reinforced-planning-with-large","title":"Entropy-Reinforced Planning with Large Language Models for Drug Discovery","date":"2024-06-11","arxiv_id":"2406.07025","n_code_links":1,"syntology":null},{"paper":"/paper/fastast-accelerating-audio-spectrogram","slug":"fastast-accelerating-audio-spectrogram","title":"FastAST: Accelerating Audio Spectrogram Transformer via Token Merging and Cross-Model Knowledge Distillation","date":"2024-06-11","arxiv_id":"2406.07676","n_code_links":1,"syntology":null},{"paper":null,"slug":"grapevine-disease-prediction-using-climate","title":"Grapevine Disease Prediction Using Climate Variables from Multi-Sensor Remote Sensing Imagery via a Transformer Model","date":"2024-06-11","arxiv_id":"2406.07094","n_code_links":0,"syntology":null},{"paper":null,"slug":"gridpe-unifying-positional-encoding-in","title":"GridPE: Unifying Positional Encoding in Transformers with a Grid Cell-Inspired Framework","date":"2024-06-11","arxiv_id":"2406.07049","n_code_links":0,"syntology":null},{"paper":"/paper/mllmguard-a-multi-dimensional-safety","slug":"mllmguard-a-multi-dimensional-safety","title":"MLLMGuard: A Multi-dimensional Safety Evaluation Suite for Multimodal Large Language Models","date":"2024-06-11","arxiv_id":"2406.07594","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["Carol-gutianle/MLLMGuard"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"towards-generalized-hydrological-forecasting","title":"Towards Generalized Hydrological Forecasting using Transformer Models for 120-Hour Streamflow Prediction","date":"2024-06-11","arxiv_id":"2406.07484","n_code_links":0,"syntology":null},{"paper":null,"slug":"validating-llm-generated-programs-with","title":"Validating LLM-Generated Programs with Metamorphic Prompt Testing","date":"2024-06-11","arxiv_id":"2406.06864","n_code_links":0,"syntology":null},{"paper":null,"slug":"annotation-alignment-comparing-llm-and-human","title":"Annotation alignment: Comparing LLM and human annotations of conversational safety","date":"2024-06-10","arxiv_id":"2406.06369","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-language-models-serve-as-text-based-world","title":"Can Language Models Serve as Text-Based World Simulators?","date":"2024-06-10","arxiv_id":"2406.06485","n_code_links":0,"syntology":null},{"paper":"/paper/data-efficient-learning-with-neural-programs","slug":"data-efficient-learning-with-neural-programs","title":"Data-Efficient Learning with Neural Programs","date":"2024-06-10","arxiv_id":"2406.06246","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":4,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["alaiasolkobreslin/ised"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/diving-into-underwater-segment-anything-model","slug":"diving-into-underwater-segment-anything-model","title":"Diving into Underwater: Segment Anything Model Guided Underwater Salient Instance Segmentation and A Large-scale Dataset","date":"2024-06-10","arxiv_id":"2406.06039","n_code_links":1,"syntology":null},{"paper":null,"slug":"emotion-aware-speech-self-supervised","title":"Emotion-Aware Speech Self-Supervised Representation Learning with Intensity Knowledge","date":"2024-06-10","arxiv_id":"2406.06646","n_code_links":0,"syntology":null},{"paper":"/paper/husky-a-unified-open-source-language-agent","slug":"husky-a-unified-open-source-language-agent","title":"Husky: A Unified, Open-Source Language Agent for Multi-Step Reasoning","date":"2024-06-10","arxiv_id":"2406.06469","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":3,"n_instrument":3,"unverified":0,"pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 2 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["agent-husky/husky-v1"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/in-context-learning-and-fine-tuning-gpt-for","slug":"in-context-learning-and-fine-tuning-gpt-for","title":"In-Context Learning and Fine-Tuning GPT for Argument Mining","date":"2024-06-10","arxiv_id":"2406.06699","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-physical-simulation-with-message","title":"Learning Physical Simulation with Message Passing Transformer","date":"2024-06-10","arxiv_id":"2406.06060","n_code_links":0,"syntology":null},{"paper":null,"slug":"pointabm-integrating-bidirectional-state","title":"PointABM:Integrating Bidirectional State Space Model with Multi-Head Self-Attention for Point Cloud Analysis","date":"2024-06-10","arxiv_id":"2406.06069","n_code_links":0,"syntology":null},{"paper":null,"slug":"securenet-a-comparative-study-of-deberta-and","title":"SecureNet: A Comparative Study of DeBERTa and Large Language Models for Phishing Detection","date":"2024-06-10","arxiv_id":"2406.06663","n_code_links":0,"syntology":null},{"paper":"/paper/separate-and-reconstruct-asymmetric-encoder","slug":"separate-and-reconstruct-asymmetric-encoder","title":"Separate and Reconstruct: Asymmetric Encoder-Decoder for Speech Separation","date":"2024-06-10","arxiv_id":"2406.05983","n_code_links":1,"syntology":null},{"paper":null,"slug":"symmetric-dot-product-attention-for-efficient","title":"Symmetric Dot-Product Attention for Efficient Training of BERT Language Models","date":"2024-06-10","arxiv_id":"2406.06366","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-knowledge-component-based-methodology-for","title":"A Knowledge-Component-Based Methodology for Evaluating AI Assistants","date":"2024-06-09","arxiv_id":"2406.05603","n_code_links":0,"syntology":null},{"paper":"/paper/are-large-language-models-actually-good-at","slug":"are-large-language-models-actually-good-at","title":"Are Large Language Models Actually Good at Text Style Transfer?","date":"2024-06-09","arxiv_id":"2406.05885","n_code_links":1,"syntology":null},{"paper":"/paper/convolution-and-attention-free-mamba-based","slug":"convolution-and-attention-free-mamba-based","title":"CAMS: Convolution and Attention-Free Mamba-based Cardiac Image Segmentation","date":"2024-06-09","arxiv_id":"2406.05786","n_code_links":1,"syntology":null},{"paper":null,"slug":"exploring-the-efficacy-of-large-language-1","title":"Exploring the Efficacy of Large Language Models (GPT-4) in Binary Reverse Engineering","date":"2024-06-09","arxiv_id":"2406.06637","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-memorize-sensor","title":"Large Language Models Memorize Sensor Datasets! Implications on Human Activity Recognition Research","date":"2024-06-09","arxiv_id":"2406.05900","n_code_links":0,"syntology":null},{"paper":null,"slug":"od-detr-online-distillation-for-stabilizing","title":"OD-DETR: Online Distillation for Stabilizing Training of Detection Transformer","date":"2024-06-09","arxiv_id":"2406.05791","n_code_links":0,"syntology":null},{"paper":"/paper/sinklora-enhanced-efficiency-and-chat","slug":"sinklora-enhanced-efficiency-and-chat","title":"SinkLoRA: Enhanced Efficiency and Chat Capabilities for Long-Context Large Language Models","date":"2024-06-09","arxiv_id":"2406.05678","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["dexter-gt-86/sinklora"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"paper":"/paper/smiles2dock-an-open-large-scale-multi-task","slug":"smiles2dock-an-open-large-scale-multi-task","title":"Smiles2Dock: an open large-scale multi-task dataset for ML-based molecular docking","date":"2024-06-09","arxiv_id":"2406.05738","n_code_links":1,"syntology":null},{"paper":null,"slug":"text2vp-generative-ai-for-visual-programming","title":"Text2VP: Generative AI for Visual Programming and Parametric Modeling","date":"2024-06-09","arxiv_id":"2407.07732","n_code_links":0,"syntology":null},{"paper":null,"slug":"vision-mamba-cutting-edge-classification-of","title":"Vision Mamba: Cutting-Edge Classification of Alzheimer's Disease with 3D MRI Scans","date":"2024-06-09","arxiv_id":"2406.05757","n_code_links":0,"syntology":null},{"paper":"/paper/a-fine-tuning-dataset-and-benchmark-for-large","slug":"a-fine-tuning-dataset-and-benchmark-for-large","title":"A Fine-tuning Dataset and Benchmark for Large Language Models for Protein Understanding","date":"2024-06-08","arxiv_id":"2406.05540","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["tsynbio/proteinlmdataset"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/automata-extraction-from-transformers","slug":"automata-extraction-from-transformers","title":"Automata Extraction from Transformers","date":"2024-06-08","arxiv_id":"2406.05564","n_code_links":1,"syntology":null},{"paper":null,"slug":"benchmarking-neural-decoding-backbones","title":"Benchmarking Neural Decoding Backbones towards Enhanced On-edge iBCI Applications","date":"2024-06-08","arxiv_id":"2406.06626","n_code_links":0,"syntology":null},{"paper":null,"slug":"do-llms-recognize-me-when-i-is-not-me","title":"Do LLMs Recognize me, When I is not me: Assessment of LLMs Understanding of Turkish Indexical Pronouns in Indexical Shift Contexts","date":"2024-06-08","arxiv_id":"2406.05569","n_code_links":0,"syntology":null},{"paper":null,"slug":"g-transformer-counterfactual-outcome","title":"G-Transformer: Counterfactual Outcome Prediction under Dynamic and Time-varying Treatment Regimes","date":"2024-06-08","arxiv_id":"2406.05504","n_code_links":0,"syntology":null},{"paper":null,"slug":"selfdefend-llms-can-defend-themselves-against","title":"SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Manner","date":"2024-06-08","arxiv_id":"2406.05498","n_code_links":0,"syntology":null},{"paper":null,"slug":"teaching-assistant-in-the-loop-improving","title":"Teaching-Assistant-in-the-Loop: Improving Knowledge Distillation from Imperfect Teacher Models in Low-Budget Scenarios","date":"2024-06-08","arxiv_id":"2406.05322","n_code_links":0,"syntology":null},{"paper":"/paper/toward-reliable-ad-hoc-scientific-information","slug":"toward-reliable-ad-hoc-scientific-information","title":"Toward Reliable Ad-hoc Scientific Information Extraction: A Case Study on Two Materials Datasets","date":"2024-06-08","arxiv_id":"2406.05348","n_code_links":1,"syntology":null},{"paper":"/paper/transformer-conformal-prediction-for-time","slug":"transformer-conformal-prediction-for-time","title":"Transformer Conformal Prediction for Time Series","date":"2024-06-08","arxiv_id":"2406.05332","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["Jayaos/TCPTS"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/u-net-ensemble-for-enhanced-semantic","slug":"u-net-ensemble-for-enhanced-semantic","title":"U-Net Ensemble for Enhanced Semantic Segmentation in Remote Sensing Imagery","date":"2024-06-08","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"are-large-language-models-more-empathetic","title":"Are Large Language Models More Empathetic than Humans?","date":"2024-06-07","arxiv_id":"2406.05063","n_code_links":0,"syntology":null},{"paper":null,"slug":"cdefuse-continuous-decomposition-for-infrared","title":"Conti-Fuse: A Novel Continuous Decomposition-based Fusion Framework for Infrared and Visible Images","date":"2024-06-07","arxiv_id":"2406.04689","n_code_links":0,"syntology":null},{"paper":"/paper/diving-deep-into-the-motion-representation-of","slug":"diving-deep-into-the-motion-representation-of","title":"Diving Deep into the Motion Representation of Video-Text Models","date":"2024-06-07","arxiv_id":"2406.05075","n_code_links":1,"syntology":null},{"paper":"/paper/gamebench-evaluating-strategic-reasoning","slug":"gamebench-evaluating-strategic-reasoning","title":"GameBench: Evaluating Strategic Reasoning Abilities of LLM Agents","date":"2024-06-07","arxiv_id":"2406.06613","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["Joshuaclymer/GameBench"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"hints-in-browser-benchmarking-language-models","title":"Hints-In-Browser: Benchmarking Language Models for Programming Feedback Generation","date":"2024-06-07","arxiv_id":"2406.05053","n_code_links":0,"syntology":null},{"paper":"/paper/improving-logits-based-detector-without","slug":"improving-logits-based-detector-without","title":"DALD: Improving Logits-based Detector without Logits from Black-box LLMs","date":"2024-06-07","arxiv_id":"2406.05232","n_code_links":1,"syntology":null},{"paper":"/paper/llavaguard-vlm-based-safeguards-for-vision","slug":"llavaguard-vlm-based-safeguards-for-vision","title":"LlavaGuard: An Open VLM-based Framework for Safeguarding Vision Datasets and Models","date":"2024-06-07","arxiv_id":"2406.05113","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ml-research/llavaguard"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/llms-are-not-intelligent-thinkers-introducing","slug":"llms-are-not-intelligent-thinkers-introducing","title":"LLMs Are Not Intelligent Thinkers: Introducing Mathematical Topic Tree Benchmark for Comprehensive Evaluation of LLMs","date":"2024-06-07","arxiv_id":"2406.05194","n_code_links":1,"syntology":null},{"paper":null,"slug":"logic-synthesis-with-generative-deep-neural","title":"Logic Synthesis with Generative Deep Neural Networks","date":"2024-06-07","arxiv_id":"2406.04699","n_code_links":0,"syntology":null},{"paper":null,"slug":"low-resource-cross-lingual-summarization","title":"Low-Resource Cross-Lingual Summarization through Few-Shot Learning with Large Language Models","date":"2024-06-07","arxiv_id":"2406.04630","n_code_links":0,"syntology":null},{"paper":"/paper/mixture-of-agents-enhances-large-language","slug":"mixture-of-agents-enhances-large-language","title":"Mixture-of-Agents Enhances Large Language Model Capabilities","date":"2024-06-07","arxiv_id":"2406.04692","n_code_links":3,"syntology":{"ran":3,"of":5,"n_ran_checked":1,"n_instrument":2,"unverified":2,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":null}},{"paper":null,"slug":"multiplane-prior-guided-few-shot-aerial-scene","title":"Multiplane Prior Guided Few-Shot Aerial Scene Rendering","date":"2024-06-07","arxiv_id":"2406.04961","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-interpretable-deep-local-learning","title":"Towards Interpretable Deep Local Learning with Successive Gradient Reconciliation","date":"2024-06-07","arxiv_id":"2406.05222","n_code_links":0,"syntology":null},{"paper":null,"slug":"unitst-effectively-modeling-inter-series-and","title":"UniTST: Effectively Modeling Inter-Series and Intra-Series Dependencies for Multivariate Time Series Forecasting","date":"2024-06-07","arxiv_id":"2406.04975","n_code_links":0,"syntology":null},{"paper":"/paper/are-graphs-and-gcns-necessary-for-short-term","slug":"are-graphs-and-gcns-necessary-for-short-term","title":"Are Graphs and GCNs necessary for short-term metro ridership forecasting?","date":"2024-06-06","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"benchmark-data-contamination-of-large","title":"Benchmark Data Contamination of Large Language Models: A Survey","date":"2024-06-06","arxiv_id":"2406.04244","n_code_links":0,"syntology":null},{"paper":"/paper/characterizing-similarities-and-divergences","slug":"characterizing-similarities-and-divergences","title":"Characterizing Similarities and Divergences in Conversational Tones in Humans and LLMs by Sampling with People","date":"2024-06-06","arxiv_id":"2406.04278","n_code_links":1,"syntology":null},{"paper":null,"slug":"credit-card-fraud-detection-using-advanced","title":"Credit Card Fraud Detection Using Advanced Transformer Model","date":"2024-06-06","arxiv_id":"2406.03733","n_code_links":0,"syntology":null},{"paper":null,"slug":"cross-variable-linear-integrated-enhanced","title":"Cross-variable Linear Integrated ENhanced Transformer for Photovoltaic power forecasting","date":"2024-06-06","arxiv_id":"2406.03808","n_code_links":0,"syntology":null}],"record_sha256":"6f8d1646299d82a6dc92fa13b2267876aab762110cc724c4b352230948e17c6d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}