{"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/question-answering/papers/47","list_of":"/task/question-answering","task":"Question Answering","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":47,"pages_in_order":109,"rows_per_page":100,"rows":[4601,4700],"of":10817,"counts":{"archive_papers_tagged":10817,"with_a_code_link":4171,"where_syntology_ran_a_sample":1274,"not_listed_spam_title":0,"listed":10817,"listed_where_code_ran":1274,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1073,"every_run_a_failure_of_syntologys_instrument":201,"listed_with_a_run_with_no_instrument_failure":1073,"listed_every_run_a_failure_of_syntologys_instrument":201,"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/question-answering","prev":"/task/question-answering/papers/46","next":"/task/question-answering/papers/48","papers":[{"url":null,"slug":"kogner-a-novel-framework-for-knowledge-graph","title":"KoGNER: A Novel Framework for Knowledge Graph Distillation on Biomedical Named Entity Recognition","date":"2025-03-19","arxiv_id":"2503.15737","repositories_listed":0,"syntology":null},{"url":null,"slug":"mamm-refine-a-recipe-for-improving","title":"MAMM-Refine: A Recipe for Improving Faithfulness in Generation with Multi-Agent Collaboration","date":"2025-03-19","arxiv_id":"2503.15272","repositories_listed":0,"syntology":null},{"url":null,"slug":"truthlens-a-training-free-paradigm-for","title":"TruthLens:A Training-Free Paradigm for DeepFake Detection","date":"2025-03-19","arxiv_id":"2503.15342","repositories_listed":0,"syntology":null},{"url":null,"slug":"upme-an-unsupervised-peer-review-framework","title":"UPME: An Unsupervised Peer Review Framework for Multimodal Large Language Model Evaluation","date":"2025-03-19","arxiv_id":"2503.14941","repositories_listed":0,"syntology":null},{"url":null,"slug":"care-a-qlora-fine-tuned-multi-domain-chatbot","title":"CARE: A QLoRA-Fine Tuned Multi-Domain Chatbot With Fast Learning On Minimal Hardware","date":"2025-03-18","arxiv_id":"2503.14136","repositories_listed":0,"syntology":null},{"url":null,"slug":"eiad-explainable-industrial-anomaly-detection","title":"EIAD: Explainable Industrial Anomaly Detection Via Multi-Modal Large Language Models","date":"2025-03-18","arxiv_id":"2503.14162","repositories_listed":0,"syntology":null},{"url":null,"slug":"identifying-and-mitigating-position-bias-of","title":"Identifying and Mitigating Position Bias of Multi-image Vision-Language Models","date":"2025-03-18","arxiv_id":"2503.13792","repositories_listed":0,"syntology":null},{"url":"/paper/marten-visual-question-answering-with-mask","slug":"marten-visual-question-answering-with-mask","title":"Marten: Visual Question Answering with Mask Generation for Multi-modal Document Understanding","date":"2025-03-18","arxiv_id":"2503.14140","repositories_listed":0,"syntology":{"n":3,"n_ran":3,"n_constructed":3,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"3 ran (of which 3 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; every one of the 3 samples that ran constructed an object rather than computing a result","sample_list":"/paper/marten-visual-question-answering-with-mask#ran","syntology_url":"https://syntology.ai/paper/2503.14140","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.14140"}},"official":null}},{"url":null,"slug":"synthetic-clarification-and-correction","title":"Synthetic Clarification and Correction Dialogues about Data-Centric Tasks -- A Teacher-Student Approach","date":"2025-03-18","arxiv_id":"2503.14167","repositories_listed":0,"syntology":null},{"url":null,"slug":"synthetic-data-generation-using-large","title":"Synthetic Data Generation Using Large Language Models: Advances in Text and Code","date":"2025-03-18","arxiv_id":"2503.14023","repositories_listed":0,"syntology":null},{"url":null,"slug":"uncertainty-distillation-teaching-language","title":"Uncertainty Distillation: Teaching Language Models to Express Semantic Confidence","date":"2025-03-18","arxiv_id":"2503.14749","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-head-to-tail-towards-balanced","title":"From Head to Tail: Towards Balanced Representation in Large Vision-Language Models through Adaptive Data Calibration","date":"2025-03-17","arxiv_id":"2503.12821","repositories_listed":0,"syntology":null},{"url":null,"slug":"his-gpt-towards-3d-human-in-scene-multimodal","title":"HIS-GPT: Towards 3D Human-In-Scene Multimodal Understanding","date":"2025-03-17","arxiv_id":"2503.12955","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-aware-iterative-retrieval-for-multi","title":"Knowledge-Aware Iterative Retrieval for Multi-Agent Systems","date":"2025-03-17","arxiv_id":"2503.13275","repositories_listed":0,"syntology":null},{"url":null,"slug":"logic-in-frames-dynamic-keyframe-search-via","title":"Logic-in-Frames: Dynamic Keyframe Search via Visual Semantic-Logical Verification for Long Video Understanding","date":"2025-03-17","arxiv_id":"2503.13139","repositories_listed":0,"syntology":null},{"url":null,"slug":"long-vmnet-accelerating-long-form-video","title":"Long-VMNet: Accelerating Long-Form Video Understanding via Fixed Memory","date":"2025-03-17","arxiv_id":"2503.13707","repositories_listed":0,"syntology":null},{"url":null,"slug":"map-evaluation-and-multi-agent-enhancement-of","title":"MAP: Evaluation and Multi-Agent Enhancement of Large Language Models for Inpatient Pathways","date":"2025-03-17","arxiv_id":"2503.13205","repositories_listed":0,"syntology":null},{"url":null,"slug":"rag-rl-advancing-retrieval-augmented","title":"RAG-RL: Advancing Retrieval-Augmented Generation via RL and Curriculum Learning","date":"2025-03-17","arxiv_id":"2503.12759","repositories_listed":0,"syntology":null},{"url":null,"slug":"sightation-counts-leveraging-sighted-user","title":"Sightation Counts: Leveraging Sighted User Feedback in Building a BLV-aligned Dataset of Diagram Descriptions","date":"2025-03-17","arxiv_id":"2503.13369","repositories_listed":0,"syntology":null},{"url":null,"slug":"task-oriented-feature-compression-for","title":"Task-Oriented Feature Compression for Multimodal Understanding via Device-Edge Co-Inference","date":"2025-03-17","arxiv_id":"2503.12926","repositories_listed":0,"syntology":null},{"url":null,"slug":"unified-autoregressive-visual-generation-and","title":"Unified Autoregressive Visual Generation and Understanding with Continuous Tokens","date":"2025-03-17","arxiv_id":"2503.13436","repositories_listed":0,"syntology":null},{"url":null,"slug":"vited-video-temporal-evidence-distillation","title":"VITED: Video Temporal Evidence Distillation","date":"2025-03-17","arxiv_id":"2503.12855","repositories_listed":0,"syntology":null},{"url":null,"slug":"general-table-question-answering-via-answer","title":"General Table Question Answering via Answer-Formula Joint Generation","date":"2025-03-16","arxiv_id":"2503.12345","repositories_listed":0,"syntology":null},{"url":null,"slug":"georsmllm-a-multimodal-large-language-model","title":"GeoRSMLLM: A Multimodal Large Language Model for Vision-Language Tasks in Geoscience and Remote Sensing","date":"2025-03-16","arxiv_id":"2503.12490","repositories_listed":0,"syntology":null},{"url":null,"slug":"pebench-a-fictitious-dataset-to-benchmark","title":"PEBench: A Fictitious Dataset to Benchmark Machine Unlearning for Multimodal Large Language Models","date":"2025-03-16","arxiv_id":"2503.12545","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-the-destination-a-novel-benchmark-for","title":"Beyond the Destination: A Novel Benchmark for Exploration-Aware Embodied Question Answering","date":"2025-03-14","arxiv_id":"2503.11117","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynrsl-vlm-enhancing-autonomous-driving","title":"DynRsl-VLM: Enhancing Autonomous Driving Perception with Dynamic Resolution Vision-Language Models","date":"2025-03-14","arxiv_id":"2503.11265","repositories_listed":0,"syntology":null},{"url":null,"slug":"muss-multilevel-subset-selection-for","title":"MUSS: Multilevel Subset Selection for Relevance and Diversity","date":"2025-03-14","arxiv_id":"2503.11126","repositories_listed":0,"syntology":null},{"url":null,"slug":"umb-peranssumm-2025-enhancing-perspective","title":"UMB@PerAnsSumm 2025: Enhancing Perspective-Aware Summarization with Prompt Optimization and Supervised Fine-Tuning","date":"2025-03-14","arxiv_id":"2503.11118","repositories_listed":0,"syntology":null},{"url":null,"slug":"kv-distill-nearly-lossless-learnable-context","title":"KV-Distill: Nearly Lossless Learnable Context Compression for LLMs","date":"2025-03-13","arxiv_id":"2503.10337","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-inference-adaptively-for","title":"Learning to Inference Adaptively for Multimodal Large Language Models","date":"2025-03-13","arxiv_id":"2503.10905","repositories_listed":0,"syntology":null},{"url":null,"slug":"time-temporal-sensitive-multi-dimensional","title":"TIME: Temporal-sensitive Multi-dimensional Instruction Tuning and Benchmarking for Video-LLMs","date":"2025-03-13","arxiv_id":"2503.09994","repositories_listed":0,"syntology":null},{"url":null,"slug":"unlock-the-power-of-unlabeled-data-in","title":"Unlock the Power of Unlabeled Data in Language Driving Model","date":"2025-03-13","arxiv_id":"2503.10586","repositories_listed":0,"syntology":null},{"url":null,"slug":"everything-can-be-described-in-words-a-simple","title":"Everything Can Be Described in Words: A Simple Unified Multi-Modal Framework with Semantic and Temporal Alignment","date":"2025-03-12","arxiv_id":"2503.09081","repositories_listed":0,"syntology":null},{"url":null,"slug":"favchat-unlocking-fine-grained-facail-video","title":"FaVChat: Unlocking Fine-Grained Facail Video Understanding with Multimodal Large Language Models","date":"2025-03-12","arxiv_id":"2503.09158","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-limitations-of-vision-language-models","title":"On the Limitations of Vision-Language Models in Understanding Image Transforms","date":"2025-03-12","arxiv_id":"2503.09837","repositories_listed":0,"syntology":null},{"url":null,"slug":"surgicalvlm-agent-towards-an-interactive-ai","title":"SurgicalVLM-Agent: Towards an Interactive AI Co-Pilot for Pituitary Surgery","date":"2025-03-12","arxiv_id":"2503.09474","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-knowledge-oriented-retrieval","title":"A Survey on Knowledge-Oriented Retrieval-Augmented Generation","date":"2025-03-11","arxiv_id":"2503.10677","repositories_listed":0,"syntology":null},{"url":null,"slug":"bring-remote-sensing-object-detect-into","title":"Bring Remote Sensing Object Detect Into Nature Language Model: Using SFT Method","date":"2025-03-11","arxiv_id":"2503.08144","repositories_listed":0,"syntology":null},{"url":null,"slug":"dafe-llm-based-evaluation-through-dynamic","title":"DAFE: LLM-Based Evaluation Through Dynamic Arbitration for Free-Form Question-Answering","date":"2025-03-11","arxiv_id":"2503.08542","repositories_listed":0,"syntology":null},{"url":null,"slug":"fasionad-integrating-high-level-instruction","title":"FASIONAD++ : Integrating High-Level Instruction and Information Bottleneck in FAt-Slow fusION Systems for Enhanced Safety in Autonomous Driving with Adaptive Feedback","date":"2025-03-11","arxiv_id":"2503.08162","repositories_listed":0,"syntology":null},{"url":null,"slug":"gradient-guided-attention-map-editing-towards","title":"Gradient-guided Attention Map Editing: Towards Efficient Contextual Hallucination Mitigation","date":"2025-03-11","arxiv_id":"2503.08963","repositories_listed":0,"syntology":null},{"url":null,"slug":"seeing-and-reasoning-with-confidence","title":"Seeing and Reasoning with Confidence: Supercharging Multimodal LLMs with an Uncertainty-Aware Agentic Framework","date":"2025-03-11","arxiv_id":"2503.08308","repositories_listed":0,"syntology":null},{"url":null,"slug":"uni-textbf-f-2-ace-fine-grained-face","title":"Uni$\\textbf{F}^2$ace: Fine-grained Face Understanding and Generation with Unified Multimodal Models","date":"2025-03-11","arxiv_id":"2503.08120","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-text-to-visuals-using-llms-to-generate","title":"From Text to Visuals: Using LLMs to Generate Math Diagrams with Vector Graphics","date":"2025-03-10","arxiv_id":"2503.07429","repositories_listed":0,"syntology":null},{"url":null,"slug":"mapqa-open-domain-geospatial-question","title":"MapQA: Open-domain Geospatial Question Answering on Map Data","date":"2025-03-10","arxiv_id":"2503.07871","repositories_listed":0,"syntology":null},{"url":null,"slug":"reagent-reversible-multi-agent-reasoning-for","title":"ReAgent: Reversible Multi-Agent Reasoning for Knowledge-Enhanced Multi-Hop QA","date":"2025-03-10","arxiv_id":"2503.06951","repositories_listed":0,"syntology":null},{"url":null,"slug":"robusto-1-dataset-comparing-humans-and-vlms","title":"Robusto-1 Dataset: Comparing Humans and VLMs on real out-of-distribution Autonomous Driving VQA from Peru","date":"2025-03-10","arxiv_id":"2503.07587","repositories_listed":0,"syntology":null},{"url":null,"slug":"taking-notes-brings-focus-towards-multi-turn","title":"Taking Notes Brings Focus? Towards Multi-Turn Multimodal Dialogue Learning","date":"2025-03-10","arxiv_id":"2503.07002","repositories_listed":0,"syntology":null},{"url":null,"slug":"talking-to-gdelt-through-knowledge-graphs","title":"Talking to GDELT Through Knowledge Graphs","date":"2025-03-10","arxiv_id":"2503.07584","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-fine-grained-video-question-answering","title":"Towards Fine-Grained Video Question Answering","date":"2025-03-10","arxiv_id":"2503.06820","repositories_listed":0,"syntology":null},{"url":null,"slug":"delusions-of-large-language-models","title":"Delusions of Large Language Models","date":"2025-03-09","arxiv_id":"2503.06709","repositories_listed":0,"syntology":null},{"url":null,"slug":"green-prompting","title":"Green Prompting","date":"2025-03-09","arxiv_id":"2503.10666","repositories_listed":0,"syntology":null},{"url":null,"slug":"human-cognition-inspired-rag-with-knowledge","title":"Human Cognition Inspired RAG with Knowledge Graph for Complex Problem Solving","date":"2025-03-09","arxiv_id":"2503.06567","repositories_listed":0,"syntology":null},{"url":null,"slug":"ti-jepa-an-innovative-energy-based-joint","title":"TI-JEPA: An Innovative Energy-based Joint Embedding Strategy for Text-Image Multimodal Systems","date":"2025-03-09","arxiv_id":"2503.06380","repositories_listed":0,"syntology":null},{"url":null,"slug":"vector-quantized-feature-fields-for-fast-3d","title":"Vector Quantized Feature Fields for Fast 3D Semantic Lifting","date":"2025-03-09","arxiv_id":"2503.06469","repositories_listed":0,"syntology":null},{"url":null,"slug":"visualsimpleqa-a-benchmark-for-decoupled","title":"VisualSimpleQA: A Benchmark for Decoupled Evaluation of Large Vision-Language Models in Fact-Seeking Question Answering","date":"2025-03-09","arxiv_id":"2503.06492","repositories_listed":0,"syntology":null},{"url":null,"slug":"integrating-frequency-domain-representations","title":"Integrating Frequency-Domain Representations with Low-Rank Adaptation in Vision-Language Models","date":"2025-03-08","arxiv_id":"2503.06003","repositories_listed":0,"syntology":null},{"url":null,"slug":"moemoe-question-guided-dense-and-scalable","title":"MoEMoE: Question Guided Dense and Scalable Sparse Mixture-of-Expert for Multi-source Multi-modal Answering","date":"2025-03-08","arxiv_id":"2503.06296","repositories_listed":0,"syntology":null},{"url":null,"slug":"splattalk-3d-vqa-with-gaussian-splatting","title":"SplatTalk: 3D VQA with Gaussian Splatting","date":"2025-03-08","arxiv_id":"2503.06271","repositories_listed":0,"syntology":null},{"url":null,"slug":"statistical-guarantees-of-correctness","title":"Correctness Coverage Evaluation for Medical Multiple-Choice Question Answering Based on the Enhanced Conformal Prediction Framework","date":"2025-03-07","arxiv_id":"2503.05505","repositories_listed":0,"syntology":null},{"url":null,"slug":"architecture-for-a-trustworthy-quantum","title":"Architecture for a Trustworthy Quantum Chatbot","date":"2025-03-06","arxiv_id":"2503.04875","repositories_listed":0,"syntology":null},{"url":null,"slug":"audio-flamingo-2-an-audio-language-model-with","title":"Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities","date":"2025-03-06","arxiv_id":"2503.03983","repositories_listed":0,"syntology":null},{"url":null,"slug":"chart-hqa-a-benchmark-for-hypothetical","title":"Chart-HQA: A Benchmark for Hypothetical Question Answering in Charts","date":"2025-03-06","arxiv_id":"2503.04095","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-kgqa-a-scalable-framework-for","title":"Dynamic-KGQA: A Scalable Framework for Generating Adaptive Question Answering Datasets","date":"2025-03-06","arxiv_id":"2503.05049","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-sam-with-efficient-prompting-and","title":"Enhancing SAM with Efficient Prompting and Preference Optimization for Semi-supervised Medical Image Segmentation","date":"2025-03-06","arxiv_id":"2503.04639","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-answer-reranking-strategies-in","title":"Evaluating Answer Reranking Strategies in Time-sensitive Question Answering","date":"2025-03-06","arxiv_id":"2503.04972","repositories_listed":0,"syntology":null},{"url":null,"slug":"lvlm-compress-bench-benchmarking-the-broader","title":"LVLM-Compress-Bench: Benchmarking the Broader Impact of Large Vision-Language Model Compression","date":"2025-03-06","arxiv_id":"2503.04982","repositories_listed":0,"syntology":null},{"url":null,"slug":"fans-formal-answer-selection-for-natural","title":"FANS -- Formal Answer Selection for Natural Language Math Reasoning Using Lean4","date":"2025-03-05","arxiv_id":"2503.03238","repositories_listed":0,"syntology":null},{"url":null,"slug":"structured-outputs-enable-general-purpose","title":"Structured Outputs Enable General-Purpose LLMs to be Medical Experts","date":"2025-03-05","arxiv_id":"2503.03194","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-understanding-multi-round-large","title":"Towards Understanding Multi-Round Large Language Model Reasoning: Approximability, Learnability and Generalizability","date":"2025-03-05","arxiv_id":"2503.03128","repositories_listed":0,"syntology":null},{"url":null,"slug":"vision-language-models-struggle-to-align","title":"Vision-Language Models Struggle to Align Entities across Modalities","date":"2025-03-05","arxiv_id":"2503.03854","repositories_listed":0,"syntology":null},{"url":null,"slug":"echoqa-a-large-collection-of-instruction","title":"EchoQA: A Large Collection of Instruction Tuning Data for Echocardiogram Reports","date":"2025-03-04","arxiv_id":"2503.02365","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimizing-open-domain-question-answering","title":"Optimizing open-domain question answering with graph-based retrieval augmented generation","date":"2025-03-04","arxiv_id":"2503.02922","repositories_listed":0,"syntology":null},{"url":null,"slug":"owlviz-an-open-world-benchmark-for-visual","title":"OWLViz: An Open-World Benchmark for Visual Question Answering","date":"2025-03-04","arxiv_id":"2503.07631","repositories_listed":0,"syntology":null},{"url":null,"slug":"2503-01606","title":"Beyond Prompting: An Efficient Embedding Framework for Open-Domain Question Answering","date":"2025-03-03","arxiv_id":"2503.01606","repositories_listed":0,"syntology":null},{"url":null,"slug":"2503-01713","title":"SAGE: A Framework of Precise Retrieval for RAG","date":"2025-03-03","arxiv_id":"2503.01713","repositories_listed":0,"syntology":null},{"url":null,"slug":"causal-tree-extraction-from-medical-case","title":"Causal Tree Extraction from Medical Case Reports: A Novel Task for Experts-like Text Comprehension","date":"2025-03-03","arxiv_id":"2503.01302","repositories_listed":0,"syntology":null},{"url":null,"slug":"generate-discriminate-evolve-enhancing","title":"Generate, Discriminate, Evolve: Enhancing Context Faithfulness via Fine-Grained Sentence-Level Self-Evolution","date":"2025-03-03","arxiv_id":"2503.01695","repositories_listed":0,"syntology":null},{"url":null,"slug":"parameter-free-video-segmentation-for-vision","title":"Parameter-free Video Segmentation for Vision and Language Understanding","date":"2025-03-03","arxiv_id":"2503.01201","repositories_listed":0,"syntology":null},{"url":null,"slug":"srag-structured-retrieval-augmented","title":"SRAG: Structured Retrieval-Augmented Generation for Multi-Entity Question Answering over Wikipedia Graph","date":"2025-03-03","arxiv_id":"2503.01346","repositories_listed":0,"syntology":null},{"url":null,"slug":"2503-00781","title":"Towards Efficient Educational Chatbots: Benchmarking RAG Frameworks","date":"2025-03-02","arxiv_id":"2503.00781","repositories_listed":0,"syntology":null},{"url":null,"slug":"er-rag-enhance-rag-with-er-based-unified","title":"ER-RAG: Enhance RAG with ER-Based Unified Modeling of Heterogeneous Data Sources","date":"2025-03-02","arxiv_id":"2504.06271","repositories_listed":0,"syntology":null},{"url":null,"slug":"funbench-benchmarking-fundus-reading-skills","title":"FunBench: Benchmarking Fundus Reading Skills of MLLMs","date":"2025-03-02","arxiv_id":"2503.00901","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimizing-multi-hop-document-retrieval","title":"Optimizing Multi-Hop Document Retrieval Through Intermediate Representations","date":"2025-03-02","arxiv_id":"2503.04796","repositories_listed":0,"syntology":null},{"url":null,"slug":"cl-moe-enhancing-multimodal-large-language","title":"CL-MoE: Enhancing Multimodal Large Language Model with Dual Momentum Mixture-of-Experts for Continual Visual Question Answering","date":"2025-03-01","arxiv_id":"2503.00413","repositories_listed":0,"syntology":null},{"url":null,"slug":"2502-21024","title":"TempRetriever: Fusion-based Temporal Dense Passage Retrieval for Time-Sensitive Questions","date":"2025-02-28","arxiv_id":"2502.21024","repositories_listed":0,"syntology":null},{"url":null,"slug":"2503-00162","title":"PreMind: Multi-Agent Video Understanding for Advanced Indexing of Presentation-style Videos","date":"2025-02-28","arxiv_id":"2503.00162","repositories_listed":0,"syntology":null},{"url":null,"slug":"fine-grained-retrieval-augmented-generation","title":"Fine-Grained Retrieval-Augmented Generation for Visual Question Answering","date":"2025-02-28","arxiv_id":"2502.20964","repositories_listed":0,"syntology":null},{"url":null,"slug":"webfaq-a-multilingual-collection-of-natural-q","title":"WebFAQ: A Multilingual Collection of Natural Q&A Datasets for Dense Retrieval","date":"2025-02-28","arxiv_id":"2502.20936","repositories_listed":0,"syntology":null},{"url":null,"slug":"bisecting-k-means-in-rag-for-enhancing","title":"Bisecting K-Means in RAG for Enhancing Question-Answering Tasks Performance in Telecommunications","date":"2025-02-27","arxiv_id":"2502.20188","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-large-language-models-unveil-the","title":"Can Large Language Models Unveil the Mysteries? An Exploration of Their Ability to Unlock Information in Complex Scenarios","date":"2025-02-27","arxiv_id":"2502.19973","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-retrieval-to-generation-comparing","title":"From Retrieval to Generation: Comparing Different Approaches","date":"2025-02-27","arxiv_id":"2502.20245","repositories_listed":0,"syntology":null},{"url":null,"slug":"m-llm-based-video-frame-selection-for","title":"M-LLM Based Video Frame Selection for Efficient Video Understanding","date":"2025-02-27","arxiv_id":"2502.19680","repositories_listed":0,"syntology":null},{"url":null,"slug":"med-rlvr-emerging-medical-reasoning-from-a-3b","title":"Med-RLVR: Emerging Medical Reasoning from a 3B base model via reinforcement Learning","date":"2025-02-27","arxiv_id":"2502.19655","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-early-noise-dropping-for-efficient-and","title":"END: Early Noise Dropping for Efficient and Effective Context Denoising","date":"2025-02-26","arxiv_id":"2502.18915","repositories_listed":0,"syntology":null},{"url":null,"slug":"mebench-benchmarking-large-language-models","title":"MEBench: Benchmarking Large Language Models for Cross-Document Multi-Entity Question Answering","date":"2025-02-26","arxiv_id":"2502.18993","repositories_listed":0,"syntology":null},{"url":null,"slug":"medvlm-r1-incentivizing-medical-reasoning","title":"MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning","date":"2025-02-26","arxiv_id":"2502.19634","repositories_listed":0,"syntology":null},{"url":null,"slug":"nexus-o-an-omni-perceptive-and-interactive","title":"Nexus: An Omni-Perceptive And -Interactive Model for Language, Audio, And Vision","date":"2025-02-26","arxiv_id":"2503.01879","repositories_listed":0,"syntology":null},{"url":null,"slug":"talking-to-the-brain-using-large-language","title":"Talking to the brain: Using Large Language Models as Proxies to Model Brain Semantic Representation","date":"2025-02-26","arxiv_id":"2502.18725","repositories_listed":0,"syntology":null}],"record_sha256":"2f0b8dc9b0d7b6c6080ce71cd9d797ba37aed96fdd9443232be7eb5410345096","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}