{"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/common-sense-reasoning/papers/4","list_of":"/task/common-sense-reasoning","task":"Common Sense Reasoning","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":4,"pages_in_order":10,"rows_per_page":100,"rows":[301,400],"of":939,"counts":{"archive_papers_tagged":939,"with_a_code_link":325,"where_syntology_ran_a_sample":114,"not_listed_spam_title":0,"listed":939,"listed_where_code_ran":114,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":97,"every_run_a_failure_of_syntologys_instrument":17,"listed_with_a_run_with_no_instrument_failure":97,"listed_every_run_a_failure_of_syntologys_instrument":17,"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/common-sense-reasoning","prev":"/task/common-sense-reasoning/papers/3","next":"/task/common-sense-reasoning/papers/5","papers":[{"url":"/paper/explain-yourself-leveraging-language-models","slug":"explain-yourself-leveraging-language-models","title":"Explain Yourself! Leveraging Language Models for Commonsense Reasoning","date":"2019-06-06","arxiv_id":"1906.02361","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/explain-yourself-leveraging-language-models#ran","syntology_url":"https://syntology.ai/paper/1906.02361","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.02361"}},"official":null}},{"url":"/paper/codah-an-adversarially-authored-question","slug":"codah-an-adversarially-authored-question","title":"CODAH: An Adversarially-Authored Question Answering Dataset for Common Sense","date":"2019-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/socialiqa-commonsense-reasoning-about-social","slug":"socialiqa-commonsense-reasoning-about-social","title":"SocialIQA: Commonsense Reasoning about Social Interactions","date":"2019-04-22","arxiv_id":"1904.09728","repositories_listed":1,"syntology":{"n":10,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"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","sample_list":"/paper/socialiqa-commonsense-reasoning-about-social#ran","syntology_url":"https://syntology.ai/paper/1904.09728","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.09728"}},"official":null}},{"url":"/paper/cite-a-corpus-of-image-text-discourse","slug":"cite-a-corpus-of-image-text-discourse","title":"CITE: A Corpus of Image-Text Discourse Relations","date":"2019-04-12","arxiv_id":"1904.06286","repositories_listed":1,"syntology":null},{"url":"/paper/asking-the-right-question-inferring-advice","slug":"asking-the-right-question-inferring-advice","title":"Asking the Right Question: Inferring Advice-Seeking Intentions from Personal Narratives","date":"2019-04-02","arxiv_id":"1904.01587","repositories_listed":1,"syntology":null},{"url":"/paper/ranking-and-selecting-multi-hop-knowledge","slug":"ranking-and-selecting-multi-hop-knowledge","title":"Ranking and Selecting Multi-Hop Knowledge Paths to Better Predict Human Needs","date":"2019-04-01","arxiv_id":"1904.00676","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-evaluation-of-common-sense-reasoning","slug":"on-the-evaluation-of-common-sense-reasoning","title":"How Reasonable are Common-Sense Reasoning Tasks: A Case-Study on the Winograd Schema Challenge and SWAG","date":"2018-11-05","arxiv_id":"1811.01778","repositories_listed":1,"syntology":null},{"url":"/paper/the-hard-core-coreference-corpus-removing","slug":"the-hard-core-coreference-corpus-removing","title":"The Knowref Coreference Corpus: Removing Gender and Number Cues for Difficult Pronominal Anaphora Resolution","date":"2018-11-02","arxiv_id":"1811.01747","repositories_listed":1,"syntology":null},{"url":"/paper/frame-and-entity-based-knowledge-for-common","slug":"frame-and-entity-based-knowledge-for-common","title":"Frame- and Entity-Based Knowledge for Common-Sense Argumentative Reasoning","date":"2018-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/deep-contextualized-word-representations-for","slug":"deep-contextualized-word-representations-for","title":"Deep contextualized word representations for detecting sarcasm and irony","date":"2018-09-26","arxiv_id":"1809.09795","repositories_listed":1,"syntology":null},{"url":"/paper/visual-coreference-resolution-in-visual","slug":"visual-coreference-resolution-in-visual","title":"Visual Coreference Resolution in Visual Dialog using Neural Module Networks","date":"2018-09-06","arxiv_id":"1809.01816","repositories_listed":1,"syntology":null},{"url":"/paper/the-interplay-between-lexical-resources-and","slug":"the-interplay-between-lexical-resources-and","title":"The Interplay between Lexical Resources and Natural Language Processing","date":"2018-07-02","arxiv_id":"1807.00571","repositories_listed":1,"syntology":null},{"url":"/paper/extracting-commonsense-properties-from","slug":"extracting-commonsense-properties-from","title":"Extracting Commonsense Properties from Embeddings with Limited Human Guidance","date":"2018-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/incorporating-chinese-characters-of-words-for","slug":"incorporating-chinese-characters-of-words-for","title":"Incorporating Chinese Characters of Words for Lexical Sememe Prediction","date":"2018-06-17","arxiv_id":"1806.06349","repositories_listed":1,"syntology":null},{"url":"/paper/gist-at-semeval-2018-task-12-a-network","slug":"gist-at-semeval-2018-task-12-a-network","title":"GIST at SemEval-2018 Task 12: A network transferring inference knowledge to Argument Reasoning Comprehension task","date":"2018-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/towards-symbolic-reinforcement-learning-with","slug":"towards-symbolic-reinforcement-learning-with","title":"Towards Symbolic Reinforcement Learning with Common Sense","date":"2018-04-23","arxiv_id":"1804.08597","repositories_listed":1,"syntology":null},{"url":"/paper/empirical-analysis-of-foundational","slug":"empirical-analysis-of-foundational","title":"Empirical Analysis of Foundational Distinctions in Linked Open Data","date":"2018-03-26","arxiv_id":"1803.09840","repositories_listed":1,"syntology":null},{"url":"/paper/acquiring-common-sense-spatial-knowledge","slug":"acquiring-common-sense-spatial-knowledge","title":"Acquiring Common Sense Spatial Knowledge through Implicit Spatial Templates","date":"2017-11-18","arxiv_id":"1711.06821","repositories_listed":1,"syntology":null},{"url":"/paper/improved-word-representation-learning-with","slug":"improved-word-representation-learning-with","title":"Improved Word Representation Learning with Sememes","date":"2017-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/an-evaluation-of-predpatt-and-open-ie-via","slug":"an-evaluation-of-predpatt-and-open-ie-via","title":"An Evaluation of PredPatt and Open IE via Stage 1 Semantic Role Labeling","date":"2017-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/correcting-contradictions","slug":"correcting-contradictions","title":"Correcting Contradictions","date":"2017-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/crosscat-a-fully-bayesian-nonparametric","slug":"crosscat-a-fully-bayesian-nonparametric","title":"CrossCat: A Fully Bayesian Nonparametric Method for Analyzing Heterogeneous, High Dimensional Data","date":"2015-12-03","arxiv_id":"1512.01272","repositories_listed":1,"syntology":null},{"url":"/paper/visual-word2vec-vis-w2v-learning-visually","slug":"visual-word2vec-vis-w2v-learning-visually","title":"Visual Word2Vec (vis-w2v): Learning Visually Grounded Word Embeddings Using Abstract Scenes","date":"2015-11-22","arxiv_id":"1511.07067","repositories_listed":1,"syntology":null},{"url":"/paper/modeling-user-exposure-in-recommendation","slug":"modeling-user-exposure-in-recommendation","title":"Modeling User Exposure in Recommendation","date":"2015-10-23","arxiv_id":"1510.07025","repositories_listed":1,"syntology":null},{"url":"/paper/recognition-of-sarcasms-in-tweets-based-on","slug":"recognition-of-sarcasms-in-tweets-based-on","title":"Recognition of Sarcasms in Tweets Based on Concept Level Sentiment Analysis and Supervised Learning Approaches","date":"2014-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":null,"slug":"comparing-apples-to-oranges-a-dataset","title":"Comparing Apples to Oranges: A Dataset & Analysis of LLM Humour Understanding from Traditional Puns to Topical Jokes","date":"2025-07-17","arxiv_id":"2507.13335","repositories_listed":0,"syntology":null},{"url":null,"slug":"checkmanual-a-new-challenge-and-benchmark-for-1","title":"CheckManual: A New Challenge and Benchmark for Manual-based Appliance Manipulation","date":"2025-06-11","arxiv_id":"2506.09343","repositories_listed":0,"syntology":null},{"url":null,"slug":"editinspector-a-benchmark-for-evaluation-of","title":"EditInspector: A Benchmark for Evaluation of Text-Guided Image Edits","date":"2025-06-11","arxiv_id":"2506.09988","repositories_listed":0,"syntology":null},{"url":null,"slug":"atlas-learning-to-optimally-memorize-the","title":"ATLAS: Learning to Optimally Memorize the Context at Test Time","date":"2025-05-29","arxiv_id":"2505.23735","repositories_listed":0,"syntology":null},{"url":null,"slug":"spatial-knowledge-graph-guided-multimodal","title":"Spatial Knowledge Graph-Guided Multimodal Synthesis","date":"2025-05-28","arxiv_id":"2505.22633","repositories_listed":0,"syntology":null},{"url":null,"slug":"caseedit-enhancing-localized-commonsense","title":"CaseEdit: Enhancing Localized Commonsense Reasoning via Null-Space Constrained Knowledge Editing in Small Parameter Language Models","date":"2025-05-26","arxiv_id":"2505.19383","repositories_listed":0,"syntology":null},{"url":null,"slug":"align-grag-reasoning-guided-dual-alignment","title":"Align-GRAG: Reasoning-Guided Dual Alignment for Graph Retrieval-Augmented Generation","date":"2025-05-22","arxiv_id":"2505.16237","repositories_listed":0,"syntology":null},{"url":null,"slug":"solve-synergy-of-language-vision-and-end-to","title":"SOLVE: Synergy of Language-Vision and End-to-End Networks for Autonomous Driving","date":"2025-05-22","arxiv_id":"2505.16805","repositories_listed":0,"syntology":null},{"url":null,"slug":"osora-output-dimension-and-singular-value","title":"OSoRA: Output-Dimension and Singular-Value Initialized Low-Rank Adaptation","date":"2025-05-20","arxiv_id":"2505.14350","repositories_listed":0,"syntology":null},{"url":null,"slug":"empirically-evaluating-commonsense","title":"Empirically evaluating commonsense intelligence in large language models with large-scale human judgments","date":"2025-05-15","arxiv_id":"2505.10309","repositories_listed":0,"syntology":null},{"url":null,"slug":"prodrev-a-dnn-framework-for-empowering","title":"ProdRev: A DNN framework for empowering customers using generative pre-trained transformers","date":"2025-05-14","arxiv_id":"2505.13491","repositories_listed":0,"syntology":null},{"url":null,"slug":"through-the-looking-glass-common-sense","title":"Through the Looking Glass: Common Sense Consistency Evaluation of Weird Images","date":"2025-05-12","arxiv_id":"2505.07704","repositories_listed":0,"syntology":null},{"url":null,"slug":"agentsgen-multi-agent-llm-in-the-loop-for","title":"AgentSGEN: Multi-Agent LLM in the Loop for Semantic Collaboration and GENeration of Synthetic Data","date":"2025-05-07","arxiv_id":"2505.13466","repositories_listed":0,"syntology":null},{"url":null,"slug":"scenethesis-a-language-and-vision-agentic","title":"Scenethesis: A Language and Vision Agentic Framework for 3D Scene Generation","date":"2025-05-05","arxiv_id":"2505.02836","repositories_listed":0,"syntology":null},{"url":null,"slug":"uav-vln-end-to-end-vision-language-guided","title":"UAV-VLN: End-to-End Vision Language guided Navigation for UAVs","date":"2025-04-30","arxiv_id":"2504.21432","repositories_listed":0,"syntology":null},{"url":null,"slug":"scanedit-hierarchically-guided-functional-3d","title":"ScanEdit: Hierarchically-Guided Functional 3D Scan Editing","date":"2025-04-21","arxiv_id":"2504.15049","repositories_listed":0,"syntology":null},{"url":null,"slug":"creating-full-stack-hybrid-reasoning-systems","title":"Creating 'Full-Stack' Hybrid Reasoning Systems that Prioritize and Enhance Human Intelligence","date":"2025-04-18","arxiv_id":"2504.13477","repositories_listed":0,"syntology":null},{"url":null,"slug":"shrinkage-initialization-for-smooth-learning","title":"Shrinkage Initialization for Smooth Learning of Neural Networks","date":"2025-04-12","arxiv_id":"2504.09107","repositories_listed":0,"syntology":null},{"url":null,"slug":"jepa4rec-learning-effective-language","title":"JEPA4Rec: Learning Effective Language Representations for Sequential Recommendation via Joint Embedding Predictive Architecture","date":"2025-04-10","arxiv_id":"2504.10512","repositories_listed":0,"syntology":null},{"url":null,"slug":"instructionbench-an-instructional-video","title":"InstructionBench: An Instructional Video Understanding Benchmark","date":"2025-04-07","arxiv_id":"2504.05040","repositories_listed":0,"syntology":null},{"url":null,"slug":"proposition-of-affordance-driven-environment","title":"Proposition of Affordance-Driven Environment Recognition Framework Using Symbol Networks in Large Language Models","date":"2025-04-02","arxiv_id":"2504.01644","repositories_listed":0,"syntology":null},{"url":null,"slug":"winowhat-a-parallel-corpus-of-paraphrased","title":"WinoWhat: A Parallel Corpus of Paraphrased WinoGrande Sentences with Common Sense Categorization","date":"2025-03-31","arxiv_id":"2503.23779","repositories_listed":0,"syntology":null},{"url":null,"slug":"glrd-global-local-collaborative-reason-and","title":"GLRD: Global-Local Collaborative Reason and Debate with PSL for 3D Open-Vocabulary Detection","date":"2025-03-26","arxiv_id":"2503.20682","repositories_listed":0,"syntology":null},{"url":null,"slug":"unbiasing-through-textual-descriptions","title":"Unbiasing through Textual Descriptions: Mitigating Representation Bias in Video Benchmarks","date":"2025-03-24","arxiv_id":"2503.18637","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-study-on-neuro-symbolic-artificial","title":"A Study on Neuro-Symbolic Artificial Intelligence: Healthcare Perspectives","date":"2025-03-23","arxiv_id":"2503.18213","repositories_listed":0,"syntology":null},{"url":"/paper/improving-preference-extraction-in-llms-by","slug":"improving-preference-extraction-in-llms-by","title":"Improving Preference Extraction In LLMs By Identifying Latent Knowledge Through Classifying Probes","date":"2025-03-22","arxiv_id":"2503.17755","repositories_listed":0,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/improving-preference-extraction-in-llms-by#ran","syntology_url":"https://syntology.ai/paper/2503.17755","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.17755"}},"official":null}},{"url":null,"slug":"do-i-look-like-a-cat-n-01-to-you-a-taxonomy","title":"Do I look like a `cat.n.01` to you? A Taxonomy Image Generation Benchmark","date":"2025-03-13","arxiv_id":"2503.10357","repositories_listed":0,"syntology":null},{"url":null,"slug":"hybridvla-collaborative-diffusion-and","title":"HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Model","date":"2025-03-13","arxiv_id":"2503.10631","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":"2503-01236","title":"LLM-Advisor: An LLM Benchmark for Cost-efficient Path Planning across Multiple Terrains","date":"2025-03-03","arxiv_id":"2503.01236","repositories_listed":0,"syntology":null},{"url":null,"slug":"2503-01700","title":"Code-as-Symbolic-Planner: Foundation Model-Based Robot Planning via Symbolic Code Generation","date":"2025-03-03","arxiv_id":"2503.01700","repositories_listed":0,"syntology":null},{"url":null,"slug":"personalized-causal-graph-reasoning-for-llms","title":"Personalized Causal Graph Reasoning for LLMs: A Case Study on Dietary Recommendations","date":"2025-02-28","arxiv_id":"2503.00134","repositories_listed":0,"syntology":null},{"url":null,"slug":"frida-to-the-rescue-analyzing-synthetic-data","title":"FRIDA to the Rescue! Analyzing Synthetic Data Effectiveness in Object-Based Common Sense Reasoning for Disaster Response","date":"2025-02-25","arxiv_id":"2502.18452","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-lottery-llm-hypothesis-rethinking-what","title":"The Lottery LLM Hypothesis, Rethinking What Abilities Should LLM Compression Preserve?","date":"2025-02-24","arxiv_id":"2502.17535","repositories_listed":0,"syntology":null},{"url":null,"slug":"navigating-semantic-relations-challenges-for","title":"Navigating Semantic Relations: Challenges for Language Models in Abstract Common-Sense Reasoning","date":"2025-02-19","arxiv_id":"2502.14086","repositories_listed":0,"syntology":null},{"url":null,"slug":"tell-me-why-incentivizing-explanations","title":"Tell Me Why: Incentivizing Explanations","date":"2025-02-19","arxiv_id":"2502.13410","repositories_listed":0,"syntology":null},{"url":null,"slug":"vision-based-generic-potential-function-for","title":"Vision-Based Generic Potential Function for Policy Alignment in Multi-Agent Reinforcement Learning","date":"2025-02-19","arxiv_id":"2502.13430","repositories_listed":0,"syntology":null},{"url":null,"slug":"inference-time-computations-for-llm-reasoning","title":"Inference-Time Computations for LLM Reasoning and Planning: A Benchmark and Insights","date":"2025-02-18","arxiv_id":"2502.12521","repositories_listed":0,"syntology":null},{"url":null,"slug":"plant-in-cupboard-orange-on-table-book-on","title":"Plant in Cupboard, Orange on Rably, Inat Aphone. Benchmarking Incremental Learning of Situation and Language Model using a Text-Simulated Situated Environment","date":"2025-02-17","arxiv_id":"2502.11733","repositories_listed":0,"syntology":null},{"url":null,"slug":"virac-a-vision-reasoning-agent-head-movement","title":"ViRAC: A Vision-Reasoning Agent Head Movement Control Framework in Arbitrary Virtual Environments","date":"2025-02-14","arxiv_id":"2502.10046","repositories_listed":0,"syntology":null},{"url":null,"slug":"elucidation-of-the-concept-of-consciousness","title":"Elucidation of the Concept of Consciousness from the Theory of Non-Human Communication Agents","date":"2025-02-05","arxiv_id":"2502.03508","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-models-as-common-sense","title":"Large Language Models as Common-Sense Heuristics","date":"2025-01-31","arxiv_id":"2501.18816","repositories_listed":0,"syntology":null},{"url":null,"slug":"maci-multi-agent-collaborative-intelligence","title":"MACI: Multi-Agent Collaborative Intelligence for Adaptive Reasoning and Temporal Planning","date":"2025-01-28","arxiv_id":"2501.16689","repositories_listed":0,"syntology":null},{"url":null,"slug":"physbench-benchmarking-and-enhancing-vision","title":"PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding","date":"2025-01-27","arxiv_id":"2501.16411","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-models-as-theory-of-mind-aware","title":"Large Language Models as Theory of Mind Aware Generative Agents with Counterfactual Reflection","date":"2025-01-26","arxiv_id":"2501.15355","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-a-litmus-test-for-common-sense","title":"Towards A Litmus Test for Common Sense","date":"2025-01-17","arxiv_id":"2501.09913","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-note-on-bequest-preferences-in-utility","title":"A note on bequest preferences in utility maximisation for modern tontines","date":"2025-01-15","arxiv_id":"2501.08972","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-quest-for-visual-understanding-a-journey","title":"The Quest for Visual Understanding: A Journey Through the Evolution of Visual Question Answering","date":"2025-01-13","arxiv_id":"2501.07109","repositories_listed":0,"syntology":null},{"url":null,"slug":"common-sense-is-all-you-need","title":"Common Sense Is All You Need","date":"2025-01-11","arxiv_id":"2501.06642","repositories_listed":0,"syntology":null},{"url":null,"slug":"mswa-refining-local-attention-with-multi","title":"MSWA: Refining Local Attention with Multi-ScaleWindow Attention","date":"2025-01-02","arxiv_id":"2501.01039","repositories_listed":0,"syntology":null},{"url":null,"slug":"disciple-learning-interpretable-programs-for","title":"DiSciPLE: Learning Interpretable Programs for Scientific Visual Discovery","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"fireplace-geometric-refinements-of-llm-common","title":"FirePlace: Geometric Refinements of LLM Common Sense Reasoning for 3D Object Placement","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"knowra-knowledge-retrieval-augmented-method","title":"KnowRA: Knowledge Retrieval Augmented Method for Document-level Relation Extraction with Comprehensive Reasoning Abilities","date":"2024-12-31","arxiv_id":"2501.00571","repositories_listed":0,"syntology":null},{"url":null,"slug":"vlabench-a-large-scale-benchmark-for-language","title":"VLABench: A Large-Scale Benchmark for Language-Conditioned Robotics Manipulation with Long-Horizon Reasoning Tasks","date":"2024-12-24","arxiv_id":"2412.18194","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-multimodal-social-agent","title":"A Multimodal Social Agent","date":"2024-12-11","arxiv_id":"2501.06189","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-rosetta-paradox-domain-specific","title":"The Rosetta Paradox: Domain-Specific Performance Inversions in Large Language Models","date":"2024-12-09","arxiv_id":"2412.17821","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-uncertainty-quantification-of","title":"A Survey on Uncertainty Quantification of Large Language Models: Taxonomy, Open Research Challenges, and Future Directions","date":"2024-12-07","arxiv_id":"2412.05563","repositories_listed":0,"syntology":null},{"url":null,"slug":"rethinking-annotation-for-object-detection-is","title":"Rethinking Annotation for Object Detection: Is Annotating Small-size Instances Worth Its Cost?","date":"2024-12-07","arxiv_id":"2412.05611","repositories_listed":0,"syntology":null},{"url":null,"slug":"let-s-think-var-by-var-large-language-models","title":"Let's Think Var-by-Var: Large Language Models Enable Ad Hoc Probabilistic Reasoning","date":"2024-12-03","arxiv_id":"2412.02081","repositories_listed":0,"syntology":null},{"url":null,"slug":"malt-improving-reasoning-with-multi-agent-llm","title":"MALT: Improving Reasoning with Multi-Agent LLM Training","date":"2024-12-02","arxiv_id":"2412.01928","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-knowledge-integration-for-3d-semantic","title":"Online Knowledge Integration for 3D Semantic Mapping: A Survey","date":"2024-11-27","arxiv_id":"2411.18147","repositories_listed":0,"syntology":null},{"url":null,"slug":"heie-mllm-based-hierarchical-explainable-aigc","title":"HEIE: MLLM-Based Hierarchical Explainable AIGC Image Implausibility Evaluator","date":"2024-11-26","arxiv_id":"2411.17261","repositories_listed":0,"syntology":null},{"url":null,"slug":"generating-out-of-distribution-scenarios","title":"Generating Out-Of-Distribution Scenarios Using Language Models","date":"2024-11-25","arxiv_id":"2411.16554","repositories_listed":0,"syntology":null},{"url":null,"slug":"interactive-and-expressive-code-augmented","title":"Interactive and Expressive Code-Augmented Planning with Large Language Models","date":"2024-11-21","arxiv_id":"2411.13826","repositories_listed":0,"syntology":null},{"url":null,"slug":"glover-generalizable-open-vocabulary","title":"GLOVER: Generalizable Open-Vocabulary Affordance Reasoning for Task-Oriented Grasping","date":"2024-11-19","arxiv_id":"2411.12286","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-tool-retrieval-by-leveraging-large","title":"Improving Tool Retrieval by Leveraging Large Language Models for Query Generation","date":"2024-11-17","arxiv_id":"2412.03573","repositories_listed":0,"syntology":null},{"url":null,"slug":"clasp-learning-concepts-for-time-series","title":"CLaSP: Learning Concepts for Time-Series Signals from Natural Language Supervision","date":"2024-11-13","arxiv_id":"2411.08397","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-bases-in-support-of-large-language","title":"Knowledge Bases in Support of Large Language Models for Processing Web News","date":"2024-11-13","arxiv_id":"2411.08278","repositories_listed":0,"syntology":null},{"url":null,"slug":"diffusion-as-reasoning-enhancing-object-goal","title":"Diffusion as Reasoning: Enhancing Object Goal Navigation with LLM-Biased Diffusion Model","date":"2024-10-29","arxiv_id":"2410.21842","repositories_listed":0,"syntology":null},{"url":null,"slug":"ippon-common-sense-guided-informative-path","title":"IPPON: Common Sense Guided Informative Path Planning for Object Goal Navigation","date":"2024-10-25","arxiv_id":"2410.19697","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-blind-solvers-to-logical-thinkers","title":"From Blind Solvers to Logical Thinkers: Benchmarking LLMs' Logical Integrity on Faulty Mathematical Problems","date":"2024-10-24","arxiv_id":"2410.18921","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-rl-with-llm-driven-data-synthesis-and","title":"Robust RL with LLM-Driven Data Synthesis and Policy Adaptation for Autonomous Driving","date":"2024-10-16","arxiv_id":"2410.12568","repositories_listed":0,"syntology":null},{"url":null,"slug":"vlm-see-robot-do-human-demo-video-to-robot","title":"VLM See, Robot Do: Human Demo Video to Robot Action Plan via Vision Language Model","date":"2024-10-11","arxiv_id":"2410.08792","repositories_listed":0,"syntology":null},{"url":null,"slug":"fusionsense-bridging-common-sense-vision-and","title":"FusionSense: Bridging Common Sense, Vision, and Touch for Robust Sparse-View Reconstruction","date":"2024-10-10","arxiv_id":"2410.08282","repositories_listed":0,"syntology":null},{"url":null,"slug":"offline-inverse-constrained-reinforcement","title":"Offline Inverse Constrained Reinforcement Learning for Safe-Critical Decision Making in Healthcare","date":"2024-10-10","arxiv_id":"2410.07525","repositories_listed":0,"syntology":null}],"record_sha256":"eac5e04dd0410e4e9b5f54abd992cc26519f5c5754b49b17dc0a3fb9ec77ef85","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}