{"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/attention/papers/144","list_of":"/method/attention","method":"Attention","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":144,"pages_in_order":316,"rows_per_page":100,"rows":[14301,14400],"of":31583,"counts":{"archive_papers_tagged":31583,"with_a_code_link":13473,"where_syntology_ran_a_sample":3998,"not_listed_spam_title":0,"listed":31583,"listed_where_code_ran":3998,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3366,"every_run_a_failure_of_syntologys_instrument":632,"listed_with_a_run_with_no_instrument_failure":3366,"listed_every_run_a_failure_of_syntologys_instrument":632,"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/attention","prev":"/method/attention/papers/143","next":"/method/attention/papers/145","papers":[{"paper":null,"slug":"transformerfam-feedback-attention-is-working","title":"TransformerFAM: Feedback attention is working memory","date":"2024-04-14","arxiv_id":"2404.09173","n_code_links":0,"syntology":null},{"paper":null,"slug":"heat-head-level-parameter-efficient","title":"Rethinking Low-Rank Adaptation in Vision: Exploring Head-Level Responsiveness across Diverse Tasks","date":"2024-04-13","arxiv_id":"2404.08894","n_code_links":0,"syntology":null},{"paper":"/paper/neurit-pushing-the-limit-of-neural-inertial","slug":"neurit-pushing-the-limit-of-neural-inertial","title":"NeurIT: Pushing the Limit of Neural Inertial Tracking for Indoor Robotic IoT","date":"2024-04-13","arxiv_id":"2404.08939","n_code_links":1,"syntology":null},{"paper":"/paper/oovs-in-the-spotlight-how-to-inflect-them","slug":"oovs-in-the-spotlight-how-to-inflect-them","title":"OOVs in the Spotlight: How to Inflect them?","date":"2024-04-13","arxiv_id":"2404.08974","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-novel-vision-transformer-based-load-profile","title":"A Novel Vision Transformer based Load Profile Analysis using Load Images as Inputs","date":"2024-04-12","arxiv_id":"2404.08175","n_code_links":0,"syntology":null},{"paper":"/paper/bert-lsh-reducing-absolute-compute-for","slug":"bert-lsh-reducing-absolute-compute-for","title":"BERT-LSH: Reducing Absolute Compute For Attention","date":"2024-04-12","arxiv_id":"2404.08836","n_code_links":1,"syntology":null},{"paper":null,"slug":"calibration-reconstruction-deep-integrated","title":"Calibration & Reconstruction: Deep Integrated Language for Referring Image Segmentation","date":"2024-04-12","arxiv_id":"2404.08281","n_code_links":0,"syntology":null},{"paper":"/paper/constrained-c-test-generation-via-mixed","slug":"constrained-c-test-generation-via-mixed","title":"Constrained C-Test Generation via Mixed-Integer Programming","date":"2024-04-12","arxiv_id":"2404.08821","n_code_links":1,"syntology":null},{"paper":null,"slug":"creativeval-evaluating-creativity-of-llm","title":"CreativEval: Evaluating Creativity of LLM-Based Hardware Code Generation","date":"2024-04-12","arxiv_id":"2404.08806","n_code_links":0,"syntology":null},{"paper":"/paper/dataset-reset-policy-optimization-for-rlhf","slug":"dataset-reset-policy-optimization-for-rlhf","title":"Dataset Reset Policy Optimization for RLHF","date":"2024-04-12","arxiv_id":"2404.08495","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":2,"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":["cornell-rl/drpo"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"paper":null,"slug":"don-t-forget-to-put-the-milk-back-dataset-for","title":"\"Don't forget to put the milk back!\" Dataset for Enabling Embodied Agents to Detect Anomalous Situations","date":"2024-04-12","arxiv_id":"2404.08827","n_code_links":0,"syntology":null},{"paper":"/paper/fastlogad-log-anomaly-detection-with-mask","slug":"fastlogad-log-anomaly-detection-with-mask","title":"FastLogAD: Log Anomaly Detection with Mask-Guided Pseudo Anomaly Generation and Discrimination","date":"2024-04-12","arxiv_id":"2404.08750","n_code_links":1,"syntology":null},{"paper":null,"slug":"ifvit-interpretable-fixed-length","title":"IFViT: Interpretable Fixed-Length Representation for Fingerprint Matching via Vision Transformer","date":"2024-04-12","arxiv_id":"2404.08237","n_code_links":0,"syntology":null},{"paper":null,"slug":"is-chatgpt-transforming-academics-writing","title":"Is ChatGPT Transforming Academics' Writing Style?","date":"2024-04-12","arxiv_id":"2404.08627","n_code_links":0,"syntology":null},{"paper":"/paper/megalodon-efficient-llm-pretraining-and","slug":"megalodon-efficient-llm-pretraining-and","title":"Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length","date":"2024-04-12","arxiv_id":"2404.08801","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":1,"n_instrument":1,"unverified":1,"pointer_only":2,"phrase":"2 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; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["xuezhemax/megalodon"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"msstnet-a-multi-scale-spatio-temporal-cnn","title":"MSSTNet: A Multi-Scale Spatio-Temporal CNN-Transformer Network for Dynamic Facial Expression Recognition","date":"2024-04-12","arxiv_id":"2404.08433","n_code_links":0,"syntology":null},{"paper":"/paper/pay-attention-to-your-neighbours-training","slug":"pay-attention-to-your-neighbours-training","title":"Pay Attention to Your Neighbours: Training-Free Open-Vocabulary Semantic Segmentation","date":"2024-04-12","arxiv_id":"2404.08181","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":1,"n_instrument":3,"unverified":2,"pointer_only":2,"phrase":"4 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; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["sinahmr/naclip"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/pre-training-small-base-lms-with-fewer-tokens","slug":"pre-training-small-base-lms-with-fewer-tokens","title":"Inheritune: Training Smaller Yet More Attentive Language Models","date":"2024-04-12","arxiv_id":"2404.08634","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["sanyalsunny111/llm-inheritune"],"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":"reducing-hallucination-in-structured-outputs","title":"Reducing hallucination in structured outputs via Retrieval-Augmented Generation","date":"2024-04-12","arxiv_id":"2404.08189","n_code_links":0,"syntology":null},{"paper":null,"slug":"revisiting-code-similarity-evaluation-with","title":"Revisiting Code Similarity Evaluation with Abstract Syntax Tree Edit Distance","date":"2024-04-12","arxiv_id":"2404.08817","n_code_links":0,"syntology":null},{"paper":null,"slug":"scalability-in-building-component-data","title":"Scalability in Building Component Data Annotation: Enhancing Facade Material Classification with Synthetic Data","date":"2024-04-12","arxiv_id":"2404.08557","n_code_links":0,"syntology":null},{"paper":null,"slug":"single-image-driven-3d-viewpoint-training","title":"Single-image driven 3d viewpoint training data augmentation for effective wine label recognition","date":"2024-04-12","arxiv_id":"2404.08820","n_code_links":0,"syntology":null},{"paper":"/paper/small-models-are-still-effective-cross-domain","slug":"small-models-are-still-effective-cross-domain","title":"Small Models Are (Still) Effective Cross-Domain Argument Extractors","date":"2024-04-12","arxiv_id":"2404.08579","n_code_links":1,"syntology":null},{"paper":"/paper/amplegcg-learning-a-universal-and","slug":"amplegcg-learning-a-universal-and","title":"AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs","date":"2024-04-11","arxiv_id":"2404.07921","n_code_links":1,"syntology":null},{"paper":"/paper/automatic-generation-and-evaluation-of","slug":"automatic-generation-and-evaluation-of","title":"Automatic Generation and Evaluation of Reading Comprehension Test Items with Large Language Models","date":"2024-04-11","arxiv_id":"2404.07720","n_code_links":2,"syntology":null},{"paper":"/paper/comments-as-natural-logic-pivots-improve-code","slug":"comments-as-natural-logic-pivots-improve-code","title":"Comments as Natural Logic Pivots: Improve Code Generation via Comment Perspective","date":"2024-04-11","arxiv_id":"2404.07549","n_code_links":1,"syntology":null},{"paper":"/paper/designqa-a-multimodal-benchmark-for","slug":"designqa-a-multimodal-benchmark-for","title":"DesignQA: A Multimodal Benchmark for Evaluating Large Language Models' Understanding of Engineering Documentation","date":"2024-04-11","arxiv_id":"2404.07917","n_code_links":1,"syntology":{"ran":5,"of":10,"n_ran_checked":5,"n_instrument":0,"unverified":5,"pointer_only":10,"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) · 5 unverified","official":{"repos":["anniedoris/design_qa"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"event-enhanced-snapshot-compressive","title":"Event-Enhanced Snapshot Compressive Videography at 10K FPS","date":"2024-04-11","arxiv_id":"2404.07551","n_code_links":0,"syntology":null},{"paper":"/paper/from-words-to-numbers-your-large-language","slug":"from-words-to-numbers-your-large-language","title":"From Words to Numbers: Your Large Language Model Is Secretly A Capable Regressor When Given In-Context Examples","date":"2024-04-11","arxiv_id":"2404.07544","n_code_links":1,"syntology":{"ran":8,"of":10,"n_ran_checked":8,"n_instrument":0,"unverified":2,"pointer_only":10,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["robertvacareanu/llm4regression"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"generative-information-retrieval-evaluation","title":"Generative Information Retrieval Evaluation","date":"2024-04-11","arxiv_id":"2404.08137","n_code_links":0,"syntology":null},{"paper":null,"slug":"graph-integrated-language-transformers-for","title":"Graph Integrated Language Transformers for Next Action Prediction in Complex Phone Calls","date":"2024-04-11","arxiv_id":"2404.08155","n_code_links":0,"syntology":null},{"paper":"/paper/hgrn2-gated-linear-rnns-with-state-expansion","slug":"hgrn2-gated-linear-rnns-with-state-expansion","title":"HGRN2: Gated Linear RNNs with State Expansion","date":"2024-04-11","arxiv_id":"2404.07904","n_code_links":4,"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":["sustcsonglin/flash-linear-attention","opennlplab/hgrn2"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"hltcoe-at-trec-2023-neuclir-track","title":"HLTCOE at TREC 2023 NeuCLIR Track","date":"2024-04-11","arxiv_id":"2404.08118","n_code_links":0,"syntology":null},{"paper":null,"slug":"human-latency-conversational-turns-for-spoken","title":"Human Latency Conversational Turns for Spoken Avatar Systems","date":"2024-04-11","arxiv_id":"2404.16053","n_code_links":0,"syntology":null},{"paper":null,"slug":"latte-low-precision-approximate-attention","title":"LATTE: Low-Precision Approximate Attention with Head-wise Trainable Threshold for Efficient Transformer","date":"2024-04-11","arxiv_id":"2404.07519","n_code_links":0,"syntology":null},{"paper":null,"slug":"llm-agents-can-autonomously-exploit-one-day","title":"LLM Agents can Autonomously Exploit One-day Vulnerabilities","date":"2024-04-11","arxiv_id":"2404.08144","n_code_links":0,"syntology":null},{"paper":"/paper/lucf-net-lightweight-u-shaped-cascade-fusion","slug":"lucf-net-lightweight-u-shaped-cascade-fusion","title":"LUCF-Net: Lightweight U-shaped Cascade Fusion Network for Medical Image Segmentation","date":"2024-04-11","arxiv_id":"2404.07473","n_code_links":1,"syntology":null},{"paper":null,"slug":"medical-mt5-an-open-source-multilingual-text","title":"Medical mT5: An Open-Source Multilingual Text-to-Text LLM for The Medical Domain","date":"2024-04-11","arxiv_id":"2404.07613","n_code_links":0,"syntology":null},{"paper":null,"slug":"mm-phyqa-multimodal-physics-question","title":"MM-PhyQA: Multimodal Physics Question-Answering With Multi-Image CoT Prompting","date":"2024-04-11","arxiv_id":"2404.08704","n_code_links":0,"syntology":null},{"paper":"/paper/on-training-data-influence-of-gpt-models","slug":"on-training-data-influence-of-gpt-models","title":"On Training Data Influence of GPT Models","date":"2024-04-11","arxiv_id":"2404.07840","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 1 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; the one sample that ran constructed an object rather than computing a result","official":{"repos":["eleutherai/pythia","ernie-research/gptfluence"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"post-hurricane-building-damage-assessment","title":"Post-hurricane building damage assessment using street-view imagery and structured data: A multi-modal deep learning approach","date":"2024-04-11","arxiv_id":"2404.07399","n_code_links":0,"syntology":null},{"paper":"/paper/progressive-semantic-guided-vision","slug":"progressive-semantic-guided-vision","title":"Progressive Semantic-Guided Vision Transformer for Zero-Shot Learning","date":"2024-04-11","arxiv_id":"2404.07713","n_code_links":1,"syntology":{"ran":8,"of":8,"n_ran_checked":6,"n_instrument":2,"unverified":0,"pointer_only":8,"phrase":"8 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["shiming-chen/zslvit"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"remembering-transformer-for-continual","title":"Remembering Transformer for Continual Learning","date":"2024-04-11","arxiv_id":"2404.07518","n_code_links":0,"syntology":null},{"paper":"/paper/rumour-evaluation-with-very-large-language","slug":"rumour-evaluation-with-very-large-language","title":"Rumour Evaluation with Very Large Language Models","date":"2024-04-11","arxiv_id":"2404.16859","n_code_links":1,"syntology":null},{"paper":null,"slug":"structure-aware-fine-tuning-for-code-pre","title":"Structure-aware Fine-tuning for Code Pre-trained Models","date":"2024-04-11","arxiv_id":"2404.07471","n_code_links":0,"syntology":null},{"paper":null,"slug":"token-space-a-category-theory-framework-for","title":"Token Space: A Category Theory Framework for AI Computations","date":"2024-04-11","arxiv_id":"2404.11624","n_code_links":0,"syntology":null},{"paper":"/paper/vim-unet-vision-mamba-for-biomedical","slug":"vim-unet-vision-mamba-for-biomedical","title":"ViM-UNet: Vision Mamba for Biomedical Segmentation","date":"2024-04-11","arxiv_id":"2404.07705","n_code_links":1,"syntology":null},{"paper":"/paper/control-dag-constrained-decoding-for-non","slug":"control-dag-constrained-decoding-for-non","title":"Control-DAG: Constrained Decoding for Non-Autoregressive Directed Acyclic T5 using Weighted Finite State Automata","date":"2024-04-10","arxiv_id":"2404.06854","n_code_links":1,"syntology":null},{"paper":"/paper/dynamic-generation-of-personalities-with","slug":"dynamic-generation-of-personalities-with","title":"Dynamic Generation of Personalities with Large Language Models","date":"2024-04-10","arxiv_id":"2404.07084","n_code_links":1,"syntology":null},{"paper":null,"slug":"emotion-cause-pair-extraction-method-based-on","title":"Emotion-cause pair extraction method based on multi-granularity information and multi-module interaction","date":"2024-04-10","arxiv_id":"2404.06812","n_code_links":0,"syntology":null},{"paper":"/paper/leave-no-context-behind-efficient-infinite","slug":"leave-no-context-behind-efficient-infinite","title":"Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention","date":"2024-04-10","arxiv_id":"2404.07143","n_code_links":5,"syntology":{"ran":15,"of":16,"n_ran_checked":7,"n_instrument":8,"unverified":1,"pointer_only":6,"phrase":"15 ran (of which 4 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 2 violated, 5 with no contract checked; 8 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":"/paper/llama-vits-enhancing-tts-synthesis-with","slug":"llama-vits-enhancing-tts-synthesis-with","title":"Llama-VITS: Enhancing TTS Synthesis with Semantic Awareness","date":"2024-04-10","arxiv_id":"2404.06714","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["xincanfeng/vitsgpt"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":"/paper/nfarec-a-negative-feedback-aware-recommender","slug":"nfarec-a-negative-feedback-aware-recommender","title":"NFARec: A Negative Feedback-Aware Recommender Model","date":"2024-04-10","arxiv_id":"2404.06900","n_code_links":1,"syntology":null},{"paper":"/paper/not-all-contexts-are-equal-teaching-llms","slug":"not-all-contexts-are-equal-teaching-llms","title":"Not All Contexts Are Equal: Teaching LLMs Credibility-aware Generation","date":"2024-04-10","arxiv_id":"2404.06809","n_code_links":1,"syntology":null},{"paper":"/paper/simpler-becomes-harder-do-llms-exhibit-a","slug":"simpler-becomes-harder-do-llms-exhibit-a","title":"Simpler becomes Harder: Do LLMs Exhibit a Coherent Behavior on Simplified Corpora?","date":"2024-04-10","arxiv_id":"2404.06838","n_code_links":1,"syntology":null},{"paper":"/paper/superposition-prompting-improving-and","slug":"superposition-prompting-improving-and","title":"Superposition Prompting: Improving and Accelerating Retrieval-Augmented Generation","date":"2024-04-10","arxiv_id":"2404.06910","n_code_links":1,"syntology":null},{"paper":"/paper/all-in-one-an-empirical-study-of-gpt-for-few","slug":"all-in-one-an-empirical-study-of-gpt-for-few","title":"Heuristic-enhanced Candidates Selection strategy for GPTs tackle Few-Shot Aspect-Based Sentiment Analysis","date":"2024-04-09","arxiv_id":"2404.06063","n_code_links":1,"syntology":null},{"paper":null,"slug":"characterizing-multimodal-long-form","title":"Characterizing Multimodal Long-form Summarization: A Case Study on Financial Reports","date":"2024-04-09","arxiv_id":"2404.06162","n_code_links":0,"syntology":null},{"paper":null,"slug":"comparing-two-model-designs-for-clinical-note","title":"Comparing Two Model Designs for Clinical Note Generation; Is an LLM a Useful Evaluator of Consistency?","date":"2024-04-09","arxiv_id":"2404.06503","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-the-potential-of-large-foundation","slug":"exploring-the-potential-of-large-foundation","title":"Exploring the Potential of Large Foundation Models for Open-Vocabulary HOI Detection","date":"2024-04-09","arxiv_id":"2404.06194","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":1,"n_instrument":0,"unverified":2,"pointer_only":3,"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) · 2 unverified","official":{"repos":["ltttpku/cmd-se-release"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"generative-pre-trained-transformer-for-2","title":"Generative Pre-Trained Transformer for Symbolic Regression Base In-Context Reinforcement Learning","date":"2024-04-09","arxiv_id":"2404.06330","n_code_links":0,"syntology":null},{"paper":"/paper/internlm-xcomposer2-4khd-a-pioneering-large","slug":"internlm-xcomposer2-4khd-a-pioneering-large","title":"InternLM-XComposer2-4KHD: A Pioneering Large Vision-Language Model Handling Resolutions from 336 Pixels to 4K HD","date":"2024-04-09","arxiv_id":"2404.06512","n_code_links":2,"syntology":null},{"paper":"/paper/llm2vec-large-language-models-are-secretly","slug":"llm2vec-large-language-models-are-secretly","title":"LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders","date":"2024-04-09","arxiv_id":"2404.05961","n_code_links":1,"syntology":null},{"paper":null,"slug":"llms-reading-comprehension-is-affected-by","title":"LLMs' Reading Comprehension Is Affected by Parametric Knowledge and Struggles with Hypothetical Statements","date":"2024-04-09","arxiv_id":"2404.06283","n_code_links":0,"syntology":null},{"paper":null,"slug":"mansformer-efficient-transformer-of-mixed","title":"Efficient Concertormer for Image Deblurring and Beyond","date":"2024-04-09","arxiv_id":"2404.06135","n_code_links":0,"syntology":null},{"paper":"/paper/pgtnet-a-process-graph-transformer-network","slug":"pgtnet-a-process-graph-transformer-network","title":"PGTNet: A Process Graph Transformer Network for Remaining Time Prediction of Business Process Instances","date":"2024-04-09","arxiv_id":"2404.06267","n_code_links":1,"syntology":null},{"paper":null,"slug":"sandwich-attack-multi-language-mixture","title":"Sandwich attack: Multi-language Mixture Adaptive Attack on LLMs","date":"2024-04-09","arxiv_id":"2404.07242","n_code_links":0,"syntology":null},{"paper":"/paper/scrdit-generating-single-cell-rna-seq-data-by","slug":"scrdit-generating-single-cell-rna-seq-data-by","title":"scRDiT: Generating single-cell RNA-seq data by diffusion transformers and accelerating sampling","date":"2024-04-09","arxiv_id":"2404.06153","n_code_links":1,"syntology":null},{"paper":null,"slug":"vision2ui-a-real-world-dataset-with-layout","title":"WebCode2M: A Real-World Dataset for Code Generation from Webpage Designs","date":"2024-04-09","arxiv_id":"2404.06369","n_code_links":0,"syntology":null},{"paper":null,"slug":"comprehensive-study-on-german-language-models","title":"Comprehensive Study on German Language Models for Clinical and Biomedical Text Understanding","date":"2024-04-08","arxiv_id":"2404.05694","n_code_links":0,"syntology":null},{"paper":null,"slug":"constraining-large-language-model-for","title":"Guiding Large Language Models to Generate Computer-Parsable Content","date":"2024-04-08","arxiv_id":"2404.05499","n_code_links":0,"syntology":null},{"paper":null,"slug":"decision-transformer-for-wireless","title":"Decision Transformers for Wireless Communications: A New Paradigm of Resource Management","date":"2024-04-08","arxiv_id":"2404.05199","n_code_links":0,"syntology":null},{"paper":"/paper/deep-optics-for-video-snapshot-compressive-1","slug":"deep-optics-for-video-snapshot-compressive-1","title":"Deep Optics for Video Snapshot Compressive Imaging","date":"2024-04-08","arxiv_id":"2404.05274","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":{"repos":["pwangcs/deepopticssci"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"enhancing-lip-reading-with-multi-scale-video","title":"Enhancing Lip Reading with Multi-Scale Video and Multi-Encoder","date":"2024-04-08","arxiv_id":"2404.05466","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-interventional-reasoning","title":"Evaluating Interventional Reasoning Capabilities of Large Language Models","date":"2024-04-08","arxiv_id":"2404.05545","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluation-of-an-llm-in-identifying-logical","title":"Evaluation of an LLM in Identifying Logical Fallacies: A Call for Rigor When Adopting LLMs in HCI Research","date":"2024-04-08","arxiv_id":"2404.05213","n_code_links":0,"syntology":null},{"paper":"/paper/fighting-crime-with-transformers-empirical","slug":"fighting-crime-with-transformers-empirical","title":"Fighting crime with Transformers: Empirical analysis of address parsing methods in payment data","date":"2024-04-08","arxiv_id":"2404.05632","n_code_links":1,"syntology":null},{"paper":"/paper/hsvit-horizontally-scalable-vision","slug":"hsvit-horizontally-scalable-vision","title":"HSViT: Horizontally Scalable Vision Transformer","date":"2024-04-08","arxiv_id":"2404.05196","n_code_links":1,"syntology":null},{"paper":"/paper/llm-reasoners-new-evaluation-library-and","slug":"llm-reasoners-new-evaluation-library-and","title":"LLM Reasoners: New Evaluation, Library, and Analysis of Step-by-Step Reasoning with Large Language Models","date":"2024-04-08","arxiv_id":"2404.05221","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":0,"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":null}},{"paper":null,"slug":"ltner-large-language-model-tagging-for-named","title":"LTNER: Large Language Model Tagging for Named Entity Recognition with Contextualized Entity Marking","date":"2024-04-08","arxiv_id":"2404.05624","n_code_links":0,"syntology":null},{"paper":null,"slug":"medexpqa-multilingual-benchmarking-of-large","title":"MedExpQA: Multilingual Benchmarking of Large Language Models for Medical Question Answering","date":"2024-04-08","arxiv_id":"2404.05590","n_code_links":0,"syntology":null},{"paper":"/paper/mlp-can-be-a-good-transformer-learner","slug":"mlp-can-be-a-good-transformer-learner","title":"MLP Can Be A Good Transformer Learner","date":"2024-04-08","arxiv_id":"2404.05657","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"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":["sihaoevery/lambda_vit"],"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":"/paper/multi-head-attention-based-deep-multiple","slug":"multi-head-attention-based-deep-multiple","title":"Multi-head Attention-based Deep Multiple Instance Learning","date":"2024-04-08","arxiv_id":"2404.05362","n_code_links":1,"syntology":null},{"paper":"/paper/petkaz-at-semeval-2024-task-3-advancing","slug":"petkaz-at-semeval-2024-task-3-advancing","title":"PetKaz at SemEval-2024 Task 3: Advancing Emotion Classification with an LLM for Emotion-Cause Pair Extraction in Conversations","date":"2024-04-08","arxiv_id":"2404.05502","n_code_links":1,"syntology":null},{"paper":null,"slug":"physics-of-language-models-part-3-3-knowledge","title":"Physics of Language Models: Part 3.3, Knowledge Capacity Scaling Laws","date":"2024-04-08","arxiv_id":"2404.05405","n_code_links":0,"syntology":null},{"paper":null,"slug":"relation-extraction-using-large-language","title":"Relation Extraction Using Large Language Models: A Case Study on Acupuncture Point Locations","date":"2024-04-08","arxiv_id":"2404.05415","n_code_links":0,"syntology":null},{"paper":null,"slug":"semantic-stealth-adversarial-text-attacks-on","title":"Semantic Stealth: Adversarial Text Attacks on NLP Using Several Methods","date":"2024-04-08","arxiv_id":"2404.05159","n_code_links":0,"syntology":null},{"paper":"/paper/use-of-a-structured-knowledge-base-enhances","slug":"use-of-a-structured-knowledge-base-enhances","title":"Use of a Structured Knowledge Base Enhances Metadata Curation by Large Language Models","date":"2024-04-08","arxiv_id":"2404.05893","n_code_links":1,"syntology":null},{"paper":"/paper/xiwu-a-basis-flexible-and-learnable-llm-for","slug":"xiwu-a-basis-flexible-and-learnable-llm-for","title":"Xiwu: A Basis Flexible and Learnable LLM for High Energy Physics","date":"2024-04-08","arxiv_id":"2404.08001","n_code_links":1,"syntology":null},{"paper":"/paper/a-multi-level-framework-for-accelerating","slug":"a-multi-level-framework-for-accelerating","title":"A Multi-Level Framework for Accelerating Training Transformer Models","date":"2024-04-07","arxiv_id":"2404.07999","n_code_links":1,"syntology":{"ran":0,"of":2,"n_ran_checked":0,"n_instrument":0,"unverified":2,"pointer_only":2,"phrase":"0 ran · 2 unverified","official":{"repos":["photooon/multi-level-training-framework"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"paper":"/paper/advancing-geometric-problem-solving-a","slug":"advancing-geometric-problem-solving-a","title":"MM-MATH: Advancing Multimodal Math Evaluation with Process Evaluation and Fine-grained Classification","date":"2024-04-07","arxiv_id":"2404.05091","n_code_links":1,"syntology":null},{"paper":null,"slug":"contextual-chart-generation-for-cyber","title":"Contextual Chart Generation for Cyber Deception","date":"2024-04-07","arxiv_id":"2404.04854","n_code_links":0,"syntology":null},{"paper":"/paper/csa-trans-code-structure-aware-transformer","slug":"csa-trans-code-structure-aware-transformer","title":"CSA-Trans: Code Structure Aware Transformer for AST","date":"2024-04-07","arxiv_id":"2404.05767","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":["saeyoon17/code-structure-aware-transformer"],"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":"/paper/data-bias-according-to-bipol-men-are","slug":"data-bias-according-to-bipol-men-are","title":"Data Bias According to Bipol: Men are Naturally Right and It is the Role of Women to Follow Their Lead","date":"2024-04-07","arxiv_id":"2404.04838","n_code_links":1,"syntology":null},{"paper":"/paper/dual-scale-transformer-for-large-scale-single","slug":"dual-scale-transformer-for-large-scale-single","title":"Dual-Scale Transformer for Large-Scale Single-Pixel Imaging","date":"2024-04-07","arxiv_id":"2404.05001","n_code_links":1,"syntology":{"ran":6,"of":11,"n_ran_checked":5,"n_instrument":1,"unverified":5,"pointer_only":11,"phrase":"6 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","official":{"repos":["gang-qu/hatnet-spi"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":3,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"gvt-a-graph-based-vision-transformer-with","title":"GvT: A Graph-based Vision Transformer with Talking-Heads Utilizing Sparsity, Trained from Scratch on Small Datasets","date":"2024-04-07","arxiv_id":"2404.04924","n_code_links":0,"syntology":null},{"paper":null,"slug":"hyperbolic-learning-with-synthetic-captions","title":"Hyperbolic Learning with Synthetic Captions for Open-World Detection","date":"2024-04-07","arxiv_id":"2404.05016","n_code_links":0,"syntology":null},{"paper":null,"slug":"initial-exploration-of-zero-shot-privacy","title":"Initial Exploration of Zero-Shot Privacy Utility Tradeoffs in Tabular Data Using GPT-4","date":"2024-04-07","arxiv_id":"2404.05047","n_code_links":0,"syntology":null},{"paper":"/paper/joint-reconstruction-of-3d-human-and-object","slug":"joint-reconstruction-of-3d-human-and-object","title":"Joint Reconstruction of 3D Human and Object via Contact-Based Refinement Transformer","date":"2024-04-07","arxiv_id":"2404.04819","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":3,"n_instrument":1,"unverified":1,"pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["dqj5182/contho_release"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/lhu-net-a-light-hybrid-u-net-for-cost","slug":"lhu-net-a-light-hybrid-u-net-for-cost","title":"LHU-Net: A Light Hybrid U-Net for Cost-Efficient, High-Performance Volumetric Medical Image Segmentation","date":"2024-04-07","arxiv_id":"2404.05102","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["xmindflow/lhunet"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}}],"record_sha256":"222831e775002fc9f02bbccb2c8409f4ae5334f98531075a860f7f10b815a245","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}