{"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":"/task/chunking/papers/2","list_of":"/task/chunking","task":"Chunking","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":2,"pages_in_order":5,"rows_per_page":100,"rows":[101,200],"of":447,"counts":{"archive_papers_tagged":447,"with_a_code_link":120,"where_syntology_ran_a_sample":26,"not_listed_spam_title":0,"listed":447,"listed_where_code_ran":26,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":21,"every_run_a_failure_of_syntologys_instrument":5,"listed_with_a_run_with_no_instrument_failure":21,"listed_every_run_a_failure_of_syntologys_instrument":5,"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":"/task/chunking","prev":"/task/chunking","next":"/task/chunking/papers/3","papers":[{"url":"/paper/sequence-labeling-a-practical-approach","slug":"sequence-labeling-a-practical-approach","title":"Sequence Labeling: A Practical Approach","date":"2018-08-12","arxiv_id":"1808.03926","repositories_listed":1,"syntology":null},{"url":"/paper/contextual-string-embeddings-for-sequence","slug":"contextual-string-embeddings-for-sequence","title":"Contextual String Embeddings for Sequence Labeling","date":"2018-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/sudachi-a-japanese-tokenizer-for-business","slug":"sudachi-a-japanese-tokenizer-for-business","title":"Sudachi: a Japanese Tokenizer for Business","date":"2018-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/whats-wrong-python-a-visual-differ-and-graph","slug":"whats-wrong-python-a-visual-differ-and-graph","title":"What's Wrong, Python? -- A Visual Differ and Graph Library for NLP in Python","date":"2018-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/a-tree-search-algorithm-for-sequence-labeling","slug":"a-tree-search-algorithm-for-sequence-labeling","title":"A Tree Search Algorithm for Sequence Labeling","date":"2018-04-29","arxiv_id":"1804.10911","repositories_listed":1,"syntology":null},{"url":"/paper/a-feature-rich-vietnamese-named-entity","slug":"a-feature-rich-vietnamese-named-entity","title":"A Feature-Rich Vietnamese Named-Entity Recognition Model","date":"2018-03-12","arxiv_id":"1803.04375","repositories_listed":1,"syntology":null},{"url":"/paper/does-higher-order-lstm-have-better-accuracy","slug":"does-higher-order-lstm-have-better-accuracy","title":"Does Higher Order LSTM Have Better Accuracy for Segmenting and Labeling Sequence Data?","date":"2017-11-22","arxiv_id":"1711.08231","repositories_listed":1,"syntology":null},{"url":"/paper/robust-multilingual-part-of-speech-tagging","slug":"robust-multilingual-part-of-speech-tagging","title":"Robust Multilingual Part-of-Speech Tagging via Adversarial Training","date":"2017-11-14","arxiv_id":"1711.04903","repositories_listed":1,"syntology":null},{"url":"/paper/review-highlights-opinion-mining-on-reviews-a","slug":"review-highlights-opinion-mining-on-reviews-a","title":"Review highlights: opinion mining on reviews: a hybrid model for rule selection in aspect extraction","date":"2017-10-18","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/nnvlp-a-neural-network-based-vietnamese","slug":"nnvlp-a-neural-network-based-vietnamese","title":"NNVLP: A Neural Network-Based Vietnamese Language Processing Toolkit","date":"2017-08-24","arxiv_id":"1708.07241","repositories_listed":1,"syntology":null},{"url":"/paper/semi-supervised-sequence-tagging-with","slug":"semi-supervised-sequence-tagging-with","title":"Semi-supervised sequence tagging with bidirectional language models","date":"2017-04-29","arxiv_id":"1705.00108","repositories_listed":1,"syntology":null},{"url":"/paper/neural-models-for-sequence-chunking","slug":"neural-models-for-sequence-chunking","title":"Neural Models for Sequence Chunking","date":"2017-01-15","arxiv_id":"1701.04027","repositories_listed":1,"syntology":null},{"url":"/paper/keystroke-dynamics-as-signal-for-shallow","slug":"keystroke-dynamics-as-signal-for-shallow","title":"Keystroke dynamics as signal for shallow syntactic parsing","date":"2016-10-11","arxiv_id":"1610.03321","repositories_listed":1,"syntology":null},{"url":"/paper/boundary-based-mwe-segmentation-with-text-1","slug":"boundary-based-mwe-segmentation-with-text-1","title":"Boundary-based MWE segmentation with text partitioning","date":"2016-08-05","arxiv_id":"1608.02025","repositories_listed":1,"syntology":null},{"url":"/paper/discourse-sense-classification-from-scratch","slug":"discourse-sense-classification-from-scratch","title":"Discourse Sense Classification from Scratch using Focused RNNs","date":"2016-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/bira-improved-predictive-exchange-word","slug":"bira-improved-predictive-exchange-word","title":"BIRA: Improved Predictive Exchange Word Clustering","date":"2016-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/evaluation-of-word-vector-representations-by","slug":"evaluation-of-word-vector-representations-by","title":"Evaluation of Word Vector Representations by Subspace Alignment","date":"2015-09-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/substitute-based-scode-word-embeddings-in","slug":"substitute-based-scode-word-embeddings-in","title":"Substitute Based SCODE Word Embeddings in Supervised NLP Tasks","date":"2014-07-25","arxiv_id":"1407.6853","repositories_listed":1,"syntology":null},{"url":"/paper/the-ai-ku-system-at-the-spmrl-2013-shared","slug":"the-ai-ku-system-at-the-spmrl-2013-shared","title":"The AI-KU System at the SPMRL 2013 Shared Task : Unsupervised Features for Dependency Parsing","date":"2013-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/named-entity-recognition-in-tweets-an","slug":"named-entity-recognition-in-tweets-an","title":"Named Entity Recognition in Tweets: An Experimental Study","date":"2011-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":null,"slug":"dynamic-chunking-for-end-to-end-hierarchical","title":"Dynamic Chunking for End-to-End Hierarchical Sequence Modeling","date":"2025-07-10","arxiv_id":"2507.07955","repositories_listed":0,"syntology":null},{"url":null,"slug":"cli-rag-a-retrieval-augmented-framework-for","title":"CLI-RAG: A Retrieval-Augmented Framework for Clinically Structured and Context Aware Text Generation with LLMs","date":"2025-07-09","arxiv_id":"2507.06715","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-llms-replace-humans-during-code-chunking","title":"Can LLMs Replace Humans During Code Chunking?","date":"2025-06-24","arxiv_id":"2506.19897","repositories_listed":0,"syntology":null},{"url":null,"slug":"cronusvla-transferring-latent-motion-across","title":"CronusVLA: Transferring Latent Motion Across Time for Multi-Frame Prediction in Manipulation","date":"2025-06-24","arxiv_id":"2506.19816","repositories_listed":0,"syntology":null},{"url":null,"slug":"chunk-twice-embed-once-a-systematic-study-of","title":"Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation","date":"2025-06-13","arxiv_id":"2506.17277","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-compression-via-question-generation","title":"Knowledge Compression via Question Generation: Enhancing Multihop Document Retrieval without Fine-tuning","date":"2025-06-09","arxiv_id":"2506.13778","repositories_listed":0,"syntology":null},{"url":null,"slug":"lid-models-are-actually-accent-classifiers","title":"LID Models are Actually Accent Classifiers: Implications and Solutions for LID on Accented Speech","date":"2025-05-31","arxiv_id":"2506.00628","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimizing-the-interface-between-knowledge","title":"Optimizing the Interface Between Knowledge Graphs and LLMs for Complex Reasoning","date":"2025-05-30","arxiv_id":"2505.24478","repositories_listed":0,"syntology":null},{"url":null,"slug":"retrieval-augmented-generation-for-service","title":"Retrieval-Augmented Generation for Service Discovery: Chunking Strategies and Benchmarking","date":"2025-05-25","arxiv_id":"2505.19310","repositories_listed":0,"syntology":null},{"url":null,"slug":"hash-rag-bridging-deep-hashing-with-retriever","title":"HASH-RAG: Bridging Deep Hashing with Retriever for Efficient, Fine Retrieval and Augmented Generation","date":"2025-05-22","arxiv_id":"2505.16133","repositories_listed":0,"syntology":null},{"url":null,"slug":"not-all-thoughts-are-generated-equal","title":"Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning","date":"2025-05-17","arxiv_id":"2505.11827","repositories_listed":0,"syntology":null},{"url":null,"slug":"concept-guided-interpretability-via-neural","title":"Concept-Guided Interpretability via Neural Chunking","date":"2025-05-16","arxiv_id":"2505.11576","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimizing-retrieval-augmented-generation-1","title":"Optimizing Retrieval-Augmented Generation: Analysis of Hyperparameter Impact on Performance and Efficiency","date":"2025-05-13","arxiv_id":"2505.08445","repositories_listed":0,"syntology":null},{"url":null,"slug":"recognizing-ornaments-in-vocal-indian-art","title":"Recognizing Ornaments in Vocal Indian Art Music with Active Annotation","date":"2025-05-07","arxiv_id":"2505.04419","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-new-hope-domain-agnostic-automatic","title":"A New HOPE: Domain-agnostic Automatic Evaluation of Text Chunking","date":"2025-05-04","arxiv_id":"2505.02171","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-token-boundaries-integrating-human","title":"Adaptive Token Boundaries: Integrating Human Chunking Mechanisms into Multimodal LLMs","date":"2025-05-03","arxiv_id":"2505.04637","repositories_listed":0,"syntology":null},{"url":null,"slug":"chorus-zero-shot-hierarchical-retrieval-and","title":"CHORUS: Zero-shot Hierarchical Retrieval and Orchestration for Generating Linear Programming Code","date":"2025-05-02","arxiv_id":"2505.01485","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-baseline-for-self-state-identification-and","title":"A Baseline for Self-state Identification and Classification in Mental Health Data: CLPsych 2025 Task","date":"2025-04-18","arxiv_id":"2504.14066","repositories_listed":0,"syntology":null},{"url":null,"slug":"bridging-industrial-expertise-and-xr-with-llm","title":"Bridging Industrial Expertise and XR with LLM-Powered Conversational Agents","date":"2025-04-07","arxiv_id":"2504.05527","repositories_listed":0,"syntology":null},{"url":null,"slug":"bi-lat-bilateral-control-based-imitation","title":"Bi-LAT: Bilateral Control-Based Imitation Learning via Natural Language and Action Chunking with Transformers","date":"2025-04-02","arxiv_id":"2504.01301","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-embedding-techniques-in-multimodal","title":"Leveraging Embedding Techniques in Multimodal Machine Learning for Mental Illness Assessment","date":"2025-04-02","arxiv_id":"2504.01767","repositories_listed":0,"syntology":null},{"url":null,"slug":"parallelflow-parallelizing-linear","title":"ParallelFlow: Parallelizing Linear Transformers via Flow Discretization","date":"2025-04-01","arxiv_id":"2504.00492","repositories_listed":0,"syntology":null},{"url":null,"slug":"niyama-breaking-the-silos-of-llm-inference","title":"Niyama : Breaking the Silos of LLM Inference Serving","date":"2025-03-28","arxiv_id":"2503.22562","repositories_listed":0,"syntology":null},{"url":null,"slug":"causalrag-integrating-causal-graphs-into","title":"CausalRAG: Integrating Causal Graphs into Retrieval-Augmented Generation","date":"2025-03-25","arxiv_id":"2503.19878","repositories_listed":0,"syntology":null},{"url":null,"slug":"slide-sliding-localized-information-for","title":"SLIDE: Sliding Localized Information for Document Extraction","date":"2025-03-23","arxiv_id":"2503.17952","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-bimanual-manipulation-via-action","title":"Learning Bimanual Manipulation via Action Chunking and Inter-Arm Coordination with Transformers","date":"2025-03-18","arxiv_id":"2503.13916","repositories_listed":0,"syntology":null},{"url":null,"slug":"accelgen-heterogeneous-slo-guaranteed-high","title":"AccelGen: Heterogeneous SLO-Guaranteed High-Throughput LLM Inference Serving for Diverse Applications","date":"2025-03-17","arxiv_id":"2503.13737","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-dionysius-emerges-apollo-learning","title":"From Dionysius Emerges Apollo -- Learning Patterns and Abstractions from Perceptual Sequences","date":"2025-03-14","arxiv_id":"2503.10973","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-pitfalls-of-imitation-learning-when","title":"The Pitfalls of Imitation Learning when Actions are Continuous","date":"2025-03-12","arxiv_id":"2503.09722","repositories_listed":0,"syntology":null},{"url":null,"slug":"chunking-the-critic-a-transformer-based-soft","title":"Chunking the Critic: A Transformer-based Soft Actor-Critic with N-Step Returns","date":"2025-03-05","arxiv_id":"2503.03660","repositories_listed":0,"syntology":null},{"url":null,"slug":"accelerating-vision-language-action-model","title":"Accelerating Vision-Language-Action Model Integrated with Action Chunking via Parallel Decoding","date":"2025-03-04","arxiv_id":"2503.02310","repositories_listed":0,"syntology":null},{"url":null,"slug":"ails-ntua-at-semeval-2025-task-4-parameter","title":"AILS-NTUA at SemEval-2025 Task 4: Parameter-Efficient Unlearning for Large Language Models using Data Chunking","date":"2025-03-04","arxiv_id":"2503.02443","repositories_listed":0,"syntology":null},{"url":null,"slug":"discovering-chunks-in-neural-embeddings-for","title":"Discovering Chunks in Neural Embeddings for Interpretability","date":"2025-02-03","arxiv_id":"2502.01803","repositories_listed":0,"syntology":null},{"url":null,"slug":"act-jepa-joint-embedding-predictive","title":"ACT-JEPA: Joint-Embedding Predictive Architecture Improves Policy Representation Learning","date":"2025-01-24","arxiv_id":"2501.14622","repositories_listed":0,"syntology":null},{"url":null,"slug":"evolution-of-diverse-and-advanced-cognitive","title":"Evolution of diverse (and advanced) cognitive abilities through adaptive fine-tuning of learning and chunking mechanisms","date":"2025-01-20","arxiv_id":"2501.11201","repositories_listed":0,"syntology":null},{"url":null,"slug":"passage-segmentation-of-documents-for","title":"Passage Segmentation of Documents for Extractive Question Answering","date":"2025-01-17","arxiv_id":"2501.09940","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-talent-employment-insights-through","title":"Enhancing Talent Employment Insights Through Feature Extraction with LLM Finetuning","date":"2025-01-13","arxiv_id":"2501.07663","repositories_listed":0,"syntology":null},{"url":null,"slug":"carbonchat-large-language-model-based","title":"CarbonChat: Large Language Model-Based Corporate Carbon Emission Analysis and Climate Knowledge Q&A System","date":"2025-01-03","arxiv_id":"2501.02031","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-retrieval-augmented-generation-framework","title":"A Retrieval-Augmented Generation Framework for Academic Literature Navigation in Data Science","date":"2024-12-19","arxiv_id":"2412.15404","repositories_listed":0,"syntology":null},{"url":null,"slug":"pca-featured-transformer-for-jamming","title":"PCA-Featured Transformer for Jamming Detection in 5G UAV Networks","date":"2024-12-19","arxiv_id":"2412.15312","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-graph-based-approach-for-conversational-ai","title":"TOBUGraph: Knowledge Graph-Based Retrieval for Enhanced LLM Performance Beyond RAG","date":"2024-12-06","arxiv_id":"2412.05447","repositories_listed":0,"syntology":null},{"url":null,"slug":"ltri-llm-streaming-long-context-inference-for","title":"Ltri-LLM: Streaming Long Context Inference for LLMs with Training-Free Dynamic Triangular Attention Pattern","date":"2024-12-06","arxiv_id":"2412.04757","repositories_listed":0,"syntology":null},{"url":null,"slug":"advanced-system-integration-analyzing-openapi","title":"Advanced System Integration: Analyzing OpenAPI Chunking for Retrieval-Augmented Generation","date":"2024-11-29","arxiv_id":"2411.19804","repositories_listed":0,"syntology":null},{"url":null,"slug":"performance-evaluation-of-geospatial-images","title":"Performance Evaluation of Geospatial Images based on Zarr and Tiff","date":"2024-11-18","arxiv_id":"2411.11291","repositories_listed":0,"syntology":null},{"url":null,"slug":"unlocking-legal-knowledge-with-multi-layered","title":"Unlocking Legal Knowledge with Multi-Layered Embedding-Based Retrieval","date":"2024-11-12","arxiv_id":"2411.07739","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm-ref-enhancing-reference-handling-in","title":"LLM-Ref: Enhancing Reference Handling in Technical Writing with Large Language Models","date":"2024-11-01","arxiv_id":"2411.00294","repositories_listed":0,"syntology":null},{"url":null,"slug":"chunkrag-novel-llm-chunk-filtering-method-for","title":"ChunkRAG: Novel LLM-Chunk Filtering Method for RAG Systems","date":"2024-10-25","arxiv_id":"2410.19572","repositories_listed":0,"syntology":null},{"url":null,"slug":"epic-efficient-position-independent-context","title":"EPIC: Efficient Position-Independent Caching for Serving Large Language Models","date":"2024-10-20","arxiv_id":"2410.15332","repositories_listed":0,"syntology":null},{"url":null,"slug":"action-abstractions-for-amortized-sampling","title":"Action abstractions for amortized sampling","date":"2024-10-19","arxiv_id":"2410.15184","repositories_listed":0,"syntology":null},{"url":null,"slug":"is-semantic-chunking-worth-the-computational","title":"Is Semantic Chunking Worth the Computational Cost?","date":"2024-10-16","arxiv_id":"2410.13070","repositories_listed":0,"syntology":null},{"url":null,"slug":"seer-self-aligned-evidence-extraction-for","title":"SEER: Self-Aligned Evidence Extraction for Retrieval-Augmented Generation","date":"2024-10-15","arxiv_id":"2410.11315","repositories_listed":0,"syntology":null},{"url":null,"slug":"scigispy-a-novel-metric-for-biomedical-text","title":"SciGisPy: a Novel Metric for Biomedical Text Simplification via Gist Inference Score","date":"2024-10-12","arxiv_id":"2410.09632","repositories_listed":0,"syntology":null},{"url":null,"slug":"uncertaintyrag-span-level-uncertainty","title":"UncertaintyRAG: Span-Level Uncertainty Enhanced Long-Context Modeling for Retrieval-Augmented Generation","date":"2024-10-03","arxiv_id":"2410.02719","repositories_listed":0,"syntology":null},{"url":null,"slug":"mnemosyne-parallelization-strategies-for","title":"Medha: Efficiently Serving Multi-Million Context Length LLM Inference Requests Without Approximations","date":"2024-09-25","arxiv_id":"2409.17264","repositories_listed":0,"syntology":null},{"url":null,"slug":"interact-inter-dependency-aware-action","title":"InterACT: Inter-dependency Aware Action Chunking with Hierarchical Attention Transformers for Bimanual Manipulation","date":"2024-09-12","arxiv_id":"2409.07914","repositories_listed":0,"syntology":null},{"url":null,"slug":"3d-gaussian-splatting-for-large-scale-3d","title":"3D Gaussian Splatting for Large-scale Surface Reconstruction from Aerial Images","date":"2024-08-31","arxiv_id":"2409.00381","repositories_listed":0,"syntology":null},{"url":null,"slug":"talklora-low-rank-adaptation-for-speech","title":"TalkLoRA: Low-Rank Adaptation for Speech-Driven Animation","date":"2024-08-25","arxiv_id":"2408.13714","repositories_listed":0,"syntology":null},{"url":null,"slug":"meta-knowledge-for-retrieval-augmented-large","title":"Meta Knowledge for Retrieval Augmented Large Language Models","date":"2024-08-16","arxiv_id":"2408.09017","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-working-memory-and-a-new-magic","title":"Hierarchical Working Memory and a New Magic Number","date":"2024-08-14","arxiv_id":"2408.07637","repositories_listed":0,"syntology":null},{"url":null,"slug":"blaze-cross-language-and-cross-project-bug","title":"BLAZE: Cross-Language and Cross-Project Bug Localization via Dynamic Chunking and Hard Example Learning","date":"2024-07-24","arxiv_id":"2407.17631","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-imitation-to-refinement-residual-rl-for","title":"From Imitation to Refinement -- Residual RL for Precise Assembly","date":"2024-07-23","arxiv_id":"2407.16677","repositories_listed":0,"syntology":null},{"url":null,"slug":"longrag-enhancing-retrieval-augmented","title":"LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMs","date":"2024-06-21","arxiv_id":"2406.15319","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-large-language-models-for-web","title":"Leveraging Large Language Models for Web Scraping","date":"2024-06-12","arxiv_id":"2406.08246","repositories_listed":0,"syntology":null},{"url":null,"slug":"equipping-transformer-with-random-access","title":"Equipping Transformer with Random-Access Reading for Long-Context Understanding","date":"2024-05-21","arxiv_id":"2405.13216","repositories_listed":0,"syntology":null},{"url":null,"slug":"pathocl-path-based-prompt-augmentation-for","title":"PathOCL: Path-Based Prompt Augmentation for OCL Generation with GPT-4","date":"2024-05-21","arxiv_id":"2405.12450","repositories_listed":0,"syntology":null},{"url":null,"slug":"exact-an-end-to-end-autonomous-excavator","title":"ExACT: An End-to-End Autonomous Excavator System Using Action Chunking With Transformers","date":"2024-05-09","arxiv_id":"2405.05861","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-view-content-aware-indexing-for-long","title":"Multi-view Content-aware Indexing for Long Document Retrieval","date":"2024-04-23","arxiv_id":"2404.15103","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-retrieval-for-rag-based-question","title":"Improving Retrieval for RAG based Question Answering Models on Financial Documents","date":"2024-03-23","arxiv_id":"2404.07221","repositories_listed":0,"syntology":null},{"url":null,"slug":"bge-landmark-embedding-a-chunking-free","title":"BGE Landmark Embedding: A Chunking-Free Embedding Method For Retrieval Augmented Long-Context Large Language Models","date":"2024-02-18","arxiv_id":"2402.11573","repositories_listed":0,"syntology":null},{"url":null,"slug":"grounding-language-model-with-chunking-free","title":"Grounding Language Model with Chunking-Free In-Context Retrieval","date":"2024-02-15","arxiv_id":"2402.09760","repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarking-and-building-long-context","title":"Benchmarking and Building Long-Context Retrieval Models with LoCo and M2-BERT","date":"2024-02-12","arxiv_id":"2402.07440","repositories_listed":0,"syntology":null},{"url":null,"slug":"releasing-the-craqan-coreference-resolution","title":"Releasing the CRaQAn (Coreference Resolution in Question-Answering): An open-source dataset and dataset creation methodology using instruction-following models","date":"2023-11-27","arxiv_id":"2311.16338","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-recurrent-connectionist-model-of-melody","title":"A recurrent connectionist model of melody perception : An exploration using TRACX2","date":"2023-11-21","arxiv_id":"2311.12431","repositories_listed":0,"syntology":null},{"url":null,"slug":"breaking-the-token-barrier-chunking-and","title":"Breaking the Token Barrier: Chunking and Convolution for Efficient Long Text Classification with BERT","date":"2023-10-31","arxiv_id":"2310.20558","repositories_listed":0,"syntology":null},{"url":null,"slug":"symmetrical-syncmap-for-imbalanced-general","title":"Symmetrical SyncMap for Imbalanced General Chunking Problems","date":"2023-10-16","arxiv_id":"2310.10045","repositories_listed":0,"syntology":null},{"url":null,"slug":"abstractive-summarization-of-large-document","title":"Abstractive Summarization of Large Document Collections Using GPT","date":"2023-10-09","arxiv_id":"2310.05690","repositories_listed":0,"syntology":null},{"url":null,"slug":"fine-tuned-vs-prompt-tuned-supervised","title":"Fine-tuned vs. Prompt-tuned Supervised Representations: Which Better Account for Brain Language Representations?","date":"2023-10-03","arxiv_id":"2310.01854","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-rwkv-for-memory-efficient-and-low","title":"Exploring RWKV for Memory Efficient and Low Latency Streaming ASR","date":"2023-09-26","arxiv_id":"2309.14758","repositories_listed":0,"syntology":null},{"url":null,"slug":"one-act-play-single-demonstration-behavior","title":"One ACT Play: Single Demonstration Behavior Cloning with Action Chunking Transformers","date":"2023-09-18","arxiv_id":"2309.10175","repositories_listed":0,"syntology":null},{"url":null,"slug":"roboagent-generalization-and-efficiency-in","title":"RoboAgent: Generalization and Efficiency in Robot Manipulation via Semantic Augmentations and Action Chunking","date":"2023-09-05","arxiv_id":"2309.01918","repositories_listed":0,"syntology":null}],"record_sha256":"c9d04d886661900111419a9428a92ad5b012a1ca3d9eeba654b12f60306effca","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}