{"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/46","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":46,"pages_in_order":109,"rows_per_page":100,"rows":[4501,4600],"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/45","next":"/task/question-answering/papers/47","papers":[{"url":null,"slug":"hd-rag-retrieval-augmented-generation-for","title":"HD-RAG: Retrieval-Augmented Generation for Hybrid Documents Containing Text and Hierarchical Tables","date":"2025-04-13","arxiv_id":"2504.09554","repositories_listed":0,"syntology":null},{"url":null,"slug":"kongzi-a-historical-large-language-model-with","title":"Kongzi: A Historical Large Language Model with Fact Enhancement","date":"2025-04-13","arxiv_id":"2504.09488","repositories_listed":0,"syntology":null},{"url":null,"slug":"notes-bank-benchmarking-neural-transcription","title":"NoTeS-Bank: Benchmarking Neural Transcription and Search for Scientific Notes Understanding","date":"2025-04-12","arxiv_id":"2504.09249","repositories_listed":0,"syntology":null},{"url":null,"slug":"pathvlm-r1-a-reinforcement-learning-driven","title":"PathVLM-R1: A Reinforcement Learning-Driven Reasoning Model for Pathology Visual-Language Tasks","date":"2025-04-12","arxiv_id":"2504.09258","repositories_listed":0,"syntology":null},{"url":null,"slug":"astrollava-towards-the-unification-of","title":"AstroLLaVA: towards the unification of astronomical data and natural language","date":"2025-04-11","arxiv_id":"2504.08583","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-graph-extended-retrieval-augmented","title":"Knowledge Graph-extended Retrieval Augmented Generation for Question Answering","date":"2025-04-11","arxiv_id":"2504.08893","repositories_listed":0,"syntology":null},{"url":null,"slug":"medhal-an-evaluation-dataset-for-medical","title":"MedHal: An Evaluation Dataset for Medical Hallucination Detection","date":"2025-04-11","arxiv_id":"2504.08596","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-efficient-and-robust-moment-retrieval","title":"Towards Efficient and Robust Moment Retrieval System: A Unified Framework for Multi-Granularity Models and Temporal Reranking","date":"2025-04-11","arxiv_id":"2504.08384","repositories_listed":0,"syntology":null},{"url":null,"slug":"vlmt-vision-language-multimodal-transformer","title":"VLMT: Vision-Language Multimodal Transformer for Multimodal Multi-hop Question Answering","date":"2025-04-11","arxiv_id":"2504.08269","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-the-frame-generating-360deg-panoramic","title":"Beyond the Frame: Generating 360° Panoramic Videos from Perspective Videos","date":"2025-04-10","arxiv_id":"2504.07940","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-metabolism-an-efficient-data-design","title":"Data Metabolism: An Efficient Data Design Schema For Vision Language Model","date":"2025-04-10","arxiv_id":"2504.12316","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhanced-question-answering-for-skill-based","title":"Enhanced Question-Answering for Skill-based learning using Knowledge-based AI and Generative AI","date":"2025-04-10","arxiv_id":"2504.07463","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-can-objects-help-video-language","title":"How Can Objects Help Video-Language Understanding?","date":"2025-04-10","arxiv_id":"2504.07454","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-temporal-question-answering","title":"On the Temporal Question-Answering Capabilities of Large Language Models Over Anonymized Data","date":"2025-04-10","arxiv_id":"2504.07646","repositories_listed":0,"syntology":null},{"url":null,"slug":"pr-attack-coordinated-prompt-rag-attacks-on","title":"PR-Attack: Coordinated Prompt-RAG Attacks on Retrieval-Augmented Generation in Large Language Models via Bilevel Optimization","date":"2025-04-10","arxiv_id":"2504.07717","repositories_listed":0,"syntology":null},{"url":null,"slug":"tale-a-tool-augmented-framework-for-reference","title":"TALE: A Tool-Augmented Framework for Reference-Free Evaluation of Large Language Models","date":"2025-04-10","arxiv_id":"2504.07385","repositories_listed":0,"syntology":null},{"url":null,"slug":"tokenfocus-vqa-enhancing-text-to-image","title":"TokenFocus-VQA: Enhancing Text-to-Image Alignment with Position-Aware Focus and Multi-Perspective Aggregations on LVLMs","date":"2025-04-10","arxiv_id":"2504.07556","repositories_listed":0,"syntology":null},{"url":null,"slug":"mdit-a-model-free-data-interpolation-method","title":"MDIT: A Model-free Data Interpolation Method for Diverse Instruction Tuning","date":"2025-04-09","arxiv_id":"2504.07288","repositories_listed":0,"syntology":null},{"url":null,"slug":"simplifying-data-integration-slm-driven","title":"Simplifying Data Integration: SLM-Driven Systems for Unified Semantic Queries Across Heterogeneous Databases","date":"2025-04-08","arxiv_id":"2504.05634","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-knowledge-graph-based-retrieval","title":"Evaluating Knowledge Graph Based Retrieval Augmented Generation Methods under Knowledge Incompleteness","date":"2025-04-07","arxiv_id":"2504.05163","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-reason-over-time-timeline-self","title":"Learning to Reason Over Time: Timeline Self-Reflection for Improved Temporal Reasoning in Language Models","date":"2025-04-07","arxiv_id":"2504.05258","repositories_listed":0,"syntology":null},{"url":null,"slug":"rs-rag-bridging-remote-sensing-imagery-and","title":"RS-RAG: Bridging Remote Sensing Imagery and Comprehensive Knowledge with a Multi-Modal Dataset and Retrieval-Augmented Generation Model","date":"2025-04-07","arxiv_id":"2504.04988","repositories_listed":0,"syntology":null},{"url":null,"slug":"synthetic-data-generation-multi-step-rl-for","title":"Synthetic Data Generation & Multi-Step RL for Reasoning & Tool Use","date":"2025-04-07","arxiv_id":"2504.04736","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-visual-text-grounding-of-multimodal","title":"Towards Visual Text Grounding of Multimodal Large Language Model","date":"2025-04-07","arxiv_id":"2504.04974","repositories_listed":0,"syntology":null},{"url":null,"slug":"advancing-egocentric-video-question-answering","title":"Advancing Egocentric Video Question Answering with Multimodal Large Language Models","date":"2025-04-06","arxiv_id":"2504.04550","repositories_listed":0,"syntology":null},{"url":null,"slug":"unirvqa-a-unified-framework-for-retrieval","title":"UniRVQA: A Unified Framework for Retrieval-Augmented Vision Question Answering via Self-Reflective Joint Training","date":"2025-04-05","arxiv_id":"2504.04065","repositories_listed":0,"syntology":null},{"url":null,"slug":"bonsai-interpretable-tree-adaptive-grounded","title":"Bonsai: Interpretable Tree-Adaptive Grounded Reasoning","date":"2025-04-04","arxiv_id":"2504.03640","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-modeling-for-medical-visual","title":"Hierarchical Modeling for Medical Visual Question Answering with Cross-Attention Fusion","date":"2025-04-04","arxiv_id":"2504.03135","repositories_listed":0,"syntology":null},{"url":null,"slug":"multilingual-retrieval-augmented-generation","title":"Multilingual Retrieval-Augmented Generation for Knowledge-Intensive Task","date":"2025-04-04","arxiv_id":"2504.03616","repositories_listed":0,"syntology":null},{"url":null,"slug":"qirl-boosting-visual-question-answering-via","title":"QIRL: Boosting Visual Question Answering via Optimized Question-Image Relation Learning","date":"2025-04-04","arxiv_id":"2504.03337","repositories_listed":0,"syntology":null},{"url":null,"slug":"adapting-large-language-models-for-multi","title":"Adapting Large Language Models for Multi-Domain Retrieval-Augmented-Generation","date":"2025-04-03","arxiv_id":"2504.02411","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-static-relationships-for-intra","title":"Leveraging Static Relationships for Intra-Type and Inter-Type Message Passing in Video Question Answering","date":"2025-04-03","arxiv_id":"2504.02417","repositories_listed":0,"syntology":null},{"url":null,"slug":"lexpam-legal-procedure-awareness-guided","title":"LexPam: Legal Procedure Awareness-Guided Mathematical Reasoning","date":"2025-04-03","arxiv_id":"2504.02590","repositories_listed":0,"syntology":null},{"url":null,"slug":"socialgesture-delving-into-multi-person","title":"SocialGesture: Delving into Multi-person Gesture Understanding","date":"2025-04-03","arxiv_id":"2504.02244","repositories_listed":0,"syntology":null},{"url":null,"slug":"biomedical-question-answering-via-multi-level","title":"Biomedical Question Answering via Multi-Level Summarization on a Local Knowledge Graph","date":"2025-04-02","arxiv_id":"2504.01309","repositories_listed":0,"syntology":null},{"url":null,"slug":"corag-collaborative-retrieval-augmented","title":"CoRAG: Collaborative Retrieval-Augmented Generation","date":"2025-04-02","arxiv_id":"2504.01883","repositories_listed":0,"syntology":null},{"url":null,"slug":"georag-a-question-answering-approach-from-a","title":"GeoRAG: A Question-Answering Approach from a Geographical Perspective","date":"2025-04-02","arxiv_id":"2504.01458","repositories_listed":0,"syntology":null},{"url":null,"slug":"gtr-graph-table-rag-for-cross-table-question","title":"GTR: Graph-Table-RAG for Cross-Table Question Answering","date":"2025-04-02","arxiv_id":"2504.01346","repositories_listed":0,"syntology":null},{"url":null,"slug":"scaling-test-time-inference-with-policy","title":"Scaling Test-Time Inference with Policy-Optimized, Dynamic Retrieval-Augmented Generation via KV Caching and Decoding","date":"2025-04-02","arxiv_id":"2504.01281","repositories_listed":0,"syntology":null},{"url":null,"slug":"automated-factual-benchmarking-for-in-car","title":"Automated Factual Benchmarking for In-Car Conversational Systems using Large Language Models","date":"2025-04-01","arxiv_id":"2504.01248","repositories_listed":0,"syntology":null},{"url":null,"slug":"cyberbot-towards-reliable-cybersecurity","title":"CyberBOT: Towards Reliable Cybersecurity Education via Ontology-Grounded Retrieval Augmented Generation","date":"2025-04-01","arxiv_id":"2504.00389","repositories_listed":0,"syntology":null},{"url":null,"slug":"mpdrive-improving-spatial-understanding-with","title":"MPDrive: Improving Spatial Understanding with Marker-Based Prompt Learning for Autonomous Driving","date":"2025-04-01","arxiv_id":"2504.00379","repositories_listed":0,"syntology":null},{"url":null,"slug":"sviqa-a-unified-speech-vision-multimodal","title":"SViQA: A Unified Speech-Vision Multimodal Model for Textless Visual Question Answering","date":"2025-04-01","arxiv_id":"2504.01049","repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-environment-interactive-planning-for","title":"Visual Environment-Interactive Planning for Embodied Complex-Question Answering","date":"2025-04-01","arxiv_id":"2504.00775","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-large-language-models-llms-for","title":"Enhancing Large Language Models (LLMs) for Telecommunications using Knowledge Graphs and Retrieval-Augmented Generation","date":"2025-03-31","arxiv_id":"2503.24245","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-analysis-of-decoding-methods-for-llm-based","title":"An Analysis of Decoding Methods for LLM-based Agents for Faithful Multi-Hop Question Answering","date":"2025-03-30","arxiv_id":"2503.23415","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-retrieval-augmented-knowledge-mining-method","title":"A Retrieval-Augmented Knowledge Mining Method with Deep Thinking LLMs for Biomedical Research and Clinical Support","date":"2025-03-29","arxiv_id":"2503.23029","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-training-free-llm-framework-with","title":"A Training-free LLM Framework with Interaction between Contextually Related Subtasks in Solving Complex Tasks","date":"2025-03-29","arxiv_id":"2503.23053","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-deepseek-v3-reason-like-a-surgeon-an","title":"Can DeepSeek Reason Like a Surgeon? An Empirical Evaluation for Vision-Language Understanding in Robotic-Assisted Surgery","date":"2025-03-29","arxiv_id":"2503.23130","repositories_listed":0,"syntology":null},{"url":null,"slug":"frem-a-flexible-reasoning-mechanism-for","title":"FReM: A Flexible Reasoning Mechanism for Balancing Quick and Slow Thinking in Long-Context Question Answering","date":"2025-03-29","arxiv_id":"2503.22985","repositories_listed":0,"syntology":null},{"url":null,"slug":"memory-aware-and-uncertainty-guided-retrieval","title":"Memory-Aware and Uncertainty-Guided Retrieval for Multi-Hop Question Answering","date":"2025-03-29","arxiv_id":"2503.23095","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-well-can-vison-language-models-understand","title":"How Well Can Vison-Language Models Understand Humans' Intention? An Open-ended Theory of Mind Question Evaluation Benchmark","date":"2025-03-28","arxiv_id":"2503.22093","repositories_listed":0,"syntology":null},{"url":null,"slug":"patience-is-all-you-need-an-agentic-system","title":"Patience is all you need! An agentic system for performing scientific literature review","date":"2025-03-28","arxiv_id":"2504.08752","repositories_listed":0,"syntology":null},{"url":null,"slug":"asksport-web-application-for-sports-question","title":"AskSport: Web Application for Sports Question-Answering","date":"2025-03-27","arxiv_id":"2503.21067","repositories_listed":0,"syntology":null},{"url":null,"slug":"assistpda-an-online-video-surveillance","title":"AssistPDA: An Online Video Surveillance Assistant for Video Anomaly Prediction, Detection, and Analysis","date":"2025-03-27","arxiv_id":"2503.21904","repositories_listed":0,"syntology":null},{"url":null,"slug":"ctrl-o-language-controllable-object-centric","title":"CTRL-O: Language-Controllable Object-Centric Visual Representation Learning","date":"2025-03-27","arxiv_id":"2503.21747","repositories_listed":0,"syntology":null},{"url":null,"slug":"jeem-vision-language-understanding-in-four","title":"JEEM: Vision-Language Understanding in Four Arabic Dialects","date":"2025-03-27","arxiv_id":"2503.21910","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-llms-with-iterative-loop-structure","title":"Leveraging LLMs with Iterative Loop Structure for Enhanced Social Intelligence in Video Question Answering","date":"2025-03-27","arxiv_id":"2503.21190","repositories_listed":0,"syntology":null},{"url":null,"slug":"meminsight-autonomous-memory-augmentation-for","title":"MemInsight: Autonomous Memory Augmentation for LLM Agents","date":"2025-03-27","arxiv_id":"2503.21760","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-of-multimodal-retrieval-augmented","title":"A Survey of Multimodal Retrieval-Augmented Generation","date":"2025-03-26","arxiv_id":"2504.08748","repositories_listed":0,"syntology":null},{"url":null,"slug":"feature4x-bridging-any-monocular-video-to-4d","title":"Feature4X: Bridging Any Monocular Video to 4D Agentic AI with Versatile Gaussian Feature Fields","date":"2025-03-26","arxiv_id":"2503.20776","repositories_listed":0,"syntology":null},{"url":null,"slug":"instruction-oriented-preference-alignment-for","title":"Instruction-Oriented Preference Alignment for Enhancing Multi-Modal Comprehension Capability of MLLMs","date":"2025-03-26","arxiv_id":"2503.20309","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigating-low-level-visual-hallucinations","title":"Mitigating Low-Level Visual Hallucinations Requires Self-Awareness: Database, Model and Training Strategy","date":"2025-03-26","arxiv_id":"2503.20673","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-res-self-reflection-in-large-vision","title":"Self-ReS: Self-Reflection in Large Vision-Language Models for Long Video Understanding","date":"2025-03-26","arxiv_id":"2503.20362","repositories_listed":0,"syntology":null},{"url":null,"slug":"vision-amplified-semantic-entropy-for","title":"Vision-Amplified Semantic Entropy for Hallucination Detection in Medical Visual Question Answering","date":"2025-03-26","arxiv_id":"2503.20504","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-vision-language-models-answer-face-to","title":"Can Vision-Language Models Answer Face to Face Questions in the Real-World?","date":"2025-03-25","arxiv_id":"2503.19356","repositories_listed":0,"syntology":null},{"url":null,"slug":"context-efficient-retrieval-with-factual","title":"Context-Efficient Retrieval with Factual Decomposition","date":"2025-03-25","arxiv_id":"2503.19574","repositories_listed":0,"syntology":null},{"url":null,"slug":"decap-context-adaptive-prompt-generation-for","title":"DeCAP: Context-Adaptive Prompt Generation for Debiasing Zero-shot Question Answering in Large Language Models","date":"2025-03-25","arxiv_id":"2503.19426","repositories_listed":0,"syntology":null},{"url":null,"slug":"domaincqa-crafting-expert-level-qa-from","title":"DomainCQA: Crafting Expert-Level QA from Domain-Specific Charts","date":"2025-03-25","arxiv_id":"2503.19498","repositories_listed":0,"syntology":null},{"url":null,"slug":"imf-implicit-fingerprint-for-large-language","title":"ImF: Implicit Fingerprint for Large Language Models","date":"2025-03-25","arxiv_id":"2503.21805","repositories_listed":0,"syntology":null},{"url":null,"slug":"improved-alignment-of-modalities-in-large","title":"Improved Alignment of Modalities in Large Vision Language Models","date":"2025-03-25","arxiv_id":"2503.19508","repositories_listed":0,"syntology":null},{"url":null,"slug":"kshseek-data-driven-approaches-to-mitigating","title":"KSHSeek: Data-Driven Approaches to Mitigating and Detecting Knowledge-Shortcut Hallucinations in Generative Models","date":"2025-03-25","arxiv_id":"2503.19482","repositories_listed":0,"syntology":null},{"url":null,"slug":"lego-puzzles-how-good-are-mllms-at-multi-step","title":"LEGO-Puzzles: How Good Are MLLMs at Multi-Step Spatial Reasoning?","date":"2025-03-25","arxiv_id":"2503.19990","repositories_listed":0,"syntology":null},{"url":"/paper/orion-a-holistic-end-to-end-autonomous","slug":"orion-a-holistic-end-to-end-autonomous","title":"ORION: A Holistic End-to-End Autonomous Driving Framework by Vision-Language Instructed Action Generation","date":"2025-03-25","arxiv_id":"2503.19755","repositories_listed":0,"syntology":null},{"url":null,"slug":"vectorfit-adaptive-singular-bias-vector-fine","title":"VectorFit : Adaptive Singular & Bias Vector Fine-Tuning of Pre-trained Foundation Models","date":"2025-03-25","arxiv_id":"2503.19530","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-of-large-language-model-agents-for","title":"A Survey of Large Language Model Agents for Question Answering","date":"2025-03-24","arxiv_id":"2503.19213","repositories_listed":0,"syntology":null},{"url":null,"slug":"din-diffusion-model-for-robust-medical-vqa","title":"DiN: Diffusion Model for Robust Medical VQA with Semantic Noisy Labels","date":"2025-03-24","arxiv_id":"2503.18536","repositories_listed":0,"syntology":null},{"url":null,"slug":"magic-vqa-multimodal-and-grounded-inference","title":"MAGIC-VQA: Multimodal And Grounded Inference with Commonsense Knowledge for Visual Question Answering","date":"2025-03-24","arxiv_id":"2503.18491","repositories_listed":0,"syntology":null},{"url":null,"slug":"open-vocabulary-functional-3d-scene-graphs","title":"Open-Vocabulary Functional 3D Scene Graphs for Real-World Indoor Spaces","date":"2025-03-24","arxiv_id":"2503.19199","repositories_listed":0,"syntology":null},{"url":null,"slug":"synthetic-function-demonstrations-improve","title":"Synthetic Function Demonstrations Improve Generation in Low-Resource Programming Languages","date":"2025-03-24","arxiv_id":"2503.18760","repositories_listed":0,"syntology":null},{"url":null,"slug":"when-is-dataset-cartography-ineffective-using","title":"When is dataset cartography ineffective? Using training dynamics does not improve robustness against Adversarial SQuAD","date":"2025-03-24","arxiv_id":"2503.18290","repositories_listed":0,"syntology":null},{"url":null,"slug":"where-is-this-coming-from-making-groundedness","title":"Where is this coming from? Making groundedness count in the evaluation of Document VQA models","date":"2025-03-24","arxiv_id":"2503.19120","repositories_listed":0,"syntology":null},{"url":null,"slug":"expanding-the-boundaries-of-vision-prior","title":"Expanding the Boundaries of Vision Prior Knowledge in Multi-modal Large Language Models","date":"2025-03-23","arxiv_id":"2503.18034","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":"sunar-semantic-uncertainty-based-neighborhood","title":"SUNAR: Semantic Uncertainty based Neighborhood Aware Retrieval for Complex QA","date":"2025-03-23","arxiv_id":"2503.17990","repositories_listed":0,"syntology":null},{"url":null,"slug":"unmasking-deceptive-visuals-benchmarking","title":"Unmasking Deceptive Visuals: Benchmarking Multimodal Large Language Models on Misleading Chart Question Answering","date":"2025-03-23","arxiv_id":"2503.18172","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-study-into-investigating-temporal","title":"A Study into Investigating Temporal Robustness of LLMs","date":"2025-03-21","arxiv_id":"2503.17073","repositories_listed":0,"syntology":null},{"url":null,"slug":"mars-a-multi-agent-framework-incorporating","title":"MARS: A Multi-Agent Framework Incorporating Socratic Guidance for Automated Prompt Optimization","date":"2025-03-21","arxiv_id":"2503.16874","repositories_listed":0,"syntology":null},{"url":null,"slug":"pvchat-personalized-video-chat-with-one-shot","title":"PVChat: Personalized Video Chat with One-Shot Learning","date":"2025-03-21","arxiv_id":"2503.17069","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-vision-centric-remote-sensing-benchmark","title":"A Vision Centric Remote Sensing Benchmark","date":"2025-03-20","arxiv_id":"2503.15816","repositories_listed":0,"syntology":null},{"url":null,"slug":"autodrive-qa-automated-generation-of-multiple","title":"AutoDrive-QA- Automated Generation of Multiple-Choice Questions for Autonomous Driving Datasets Using Large Vision-Language Models","date":"2025-03-20","arxiv_id":"2503.15778","repositories_listed":0,"syntology":null},{"url":null,"slug":"big-help-or-big-brother-auditing-tracking","title":"Big Help or Big Brother? Auditing Tracking, Profiling, and Personalization in Generative AI Assistants","date":"2025-03-20","arxiv_id":"2503.16586","repositories_listed":0,"syntology":null},{"url":null,"slug":"bridging-technology-and-humanities-evaluating","title":"Bridging Technology and Humanities: Evaluating the Impact of Large Language Models on Social Sciences Research with DeepSeek-R1","date":"2025-03-20","arxiv_id":"2503.16304","repositories_listed":0,"syntology":null},{"url":null,"slug":"docvideoqa-towards-comprehensive","title":"DocVideoQA: Towards Comprehensive Understanding of Document-Centric Videos through Question Answering","date":"2025-03-20","arxiv_id":"2503.15887","repositories_listed":0,"syntology":null},{"url":null,"slug":"eckgbench-benchmarking-large-language-models","title":"ECKGBench: Benchmarking Large Language Models in E-commerce Leveraging Knowledge Graph","date":"2025-03-20","arxiv_id":"2503.15990","repositories_listed":0,"syntology":null},{"url":"/paper/graspcot-integrating-physical-property","slug":"graspcot-integrating-physical-property","title":"GraspCoT: Integrating Physical Property Reasoning for 6-DoF Grasping under Flexible Language Instructions","date":"2025-03-20","arxiv_id":"2503.16013","repositories_listed":0,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"7 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/graspcot-integrating-physical-property#ran","syntology_url":"https://syntology.ai/paper/2503.16013","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.16013"}},"official":null}},{"url":null,"slug":"mkg-rank-enhancing-large-language-models-with","title":"MKG-Rank: Enhancing Large Language Models with Knowledge Graph for Multilingual Medical Question Answering","date":"2025-03-20","arxiv_id":"2503.16131","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficientllava-generalizable-auto-pruning-for","title":"EfficientLLaVA:Generalizable Auto-Pruning for Large Vision-language Models","date":"2025-03-19","arxiv_id":"2503.15369","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-bias-in-retrieval-augmented","title":"Bias Evaluation and Mitigation in Retrieval-Augmented Medical Question-Answering Systems","date":"2025-03-19","arxiv_id":"2503.15454","repositories_listed":0,"syntology":null},{"url":null,"slug":"graspcorrect-robotic-grasp-correction-via","title":"GraspCorrect: Robotic Grasp Correction via Vision-Language Model-Guided Feedback","date":"2025-03-19","arxiv_id":"2503.15035","repositories_listed":0,"syntology":null}],"record_sha256":"c45d4fcc88a20c4f6e2fcc9c5815919b51a0f29bc1c2ca6f894c5dd2d1c38546","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}