{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/focus/papers/7","list_of":"/method/focus","method":"Focus","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":7,"pages_in_order":154,"rows_per_page":100,"rows":[601,700],"of":15340,"counts":{"archive_papers_tagged":15340,"with_a_code_link":5193,"where_syntology_ran_a_sample":1419,"not_listed_spam_title":0,"listed":15340,"listed_where_code_ran":1419,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1210,"every_run_a_failure_of_syntologys_instrument":209,"listed_with_a_run_with_no_instrument_failure":1210,"listed_every_run_a_failure_of_syntologys_instrument":209,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/method/focus","prev":"/method/focus/papers/6","next":"/method/focus/papers/8","papers":[{"paper":null,"slug":"a-comprehensive-analysis-of-pinns-variants","title":"A comprehensive analysis of PINNs: Variants, Applications, and Challenges","date":"2025-05-28","arxiv_id":"2505.22761","n_code_links":0,"syntology":null},{"paper":null,"slug":"advancing-hearing-assessment-an-asr-based","title":"Advancing Hearing Assessment: An ASR-Based Frequency-Specific Speech Test for Diagnosing Presbycusis","date":"2025-05-28","arxiv_id":"2505.22231","n_code_links":0,"syntology":null},{"paper":null,"slug":"agent-unirag-a-trainable-open-source-llm","title":"Agent-UniRAG: A Trainable Open-Source LLM Agent Framework for Unified Retrieval-Augmented Generation Systems","date":"2025-05-28","arxiv_id":"2505.22571","n_code_links":0,"syntology":null},{"paper":"/paper/beyond-perception-evaluating-abstract-visual","slug":"beyond-perception-evaluating-abstract-visual","title":"Beyond Perception: Evaluating Abstract Visual Reasoning through Multi-Stage Task","date":"2025-05-28","arxiv_id":"2505.21850","n_code_links":1,"syntology":null},{"paper":null,"slug":"bridging-distribution-shift-and-ai-safety","title":"Bridging Distribution Shift and AI Safety: Conceptual and Methodological Synergies","date":"2025-05-28","arxiv_id":"2505.22829","n_code_links":0,"syntology":null},{"paper":"/paper/cadrille-multi-modal-cad-reconstruction-with","slug":"cadrille-multi-modal-cad-reconstruction-with","title":"cadrille: Multi-modal CAD Reconstruction with Online Reinforcement Learning","date":"2025-05-28","arxiv_id":"2505.22914","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","official":null}},{"paper":null,"slug":"current-trends-and-future-directions-in-event","title":"Current trends and future directions in event-based control","date":"2025-05-28","arxiv_id":"2505.22378","n_code_links":0,"syntology":null},{"paper":null,"slug":"er-reason-a-benchmark-dataset-for-llm-based","title":"ER-REASON: A Benchmark Dataset for LLM-Based Clinical Reasoning in the Emergency Room","date":"2025-05-28","arxiv_id":"2505.22919","n_code_links":0,"syntology":null},{"paper":null,"slug":"forecasting-residential-heating-and","title":"Forecasting Residential Heating and Electricity Demand with Scalable, High-Resolution, Open-Source Models","date":"2025-05-28","arxiv_id":"2505.22873","n_code_links":0,"syntology":null},{"paper":"/paper/irs-incremental-relationship-guided","slug":"irs-incremental-relationship-guided","title":"IRS: Incremental Relationship-guided Segmentation for Digital Pathology","date":"2025-05-28","arxiv_id":"2505.22855","n_code_links":1,"syntology":null},{"paper":null,"slug":"lamdagent-an-autonomous-framework-for-post","title":"LaMDAgent: An Autonomous Framework for Post-Training Pipeline Optimization via LLM Agents","date":"2025-05-28","arxiv_id":"2505.21963","n_code_links":0,"syntology":null},{"paper":"/paper/let-them-talk-audio-driven-multi-person","slug":"let-them-talk-audio-driven-multi-person","title":"Let Them Talk: Audio-Driven Multi-Person Conversational Video Generation","date":"2025-05-28","arxiv_id":"2505.22647","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["meigen-ai/multitalk"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/more-a-mixture-of-low-rank-experts-for","slug":"more-a-mixture-of-low-rank-experts-for","title":"MoRE: A Mixture of Low-Rank Experts for Adaptive Multi-Task Learning","date":"2025-05-28","arxiv_id":"2505.22694","n_code_links":1,"syntology":null},{"paper":null,"slug":"position-uncertainty-quantification-needs","title":"Position: Uncertainty Quantification Needs Reassessment for Large-language Model Agents","date":"2025-05-28","arxiv_id":"2505.22655","n_code_links":0,"syntology":null},{"paper":"/paper/preventing-spurious-interactions-a-new","slug":"preventing-spurious-interactions-a-new","title":"Preventing Spurious Interactions: A New Inductive Bias for Accurate Treatment Effect Estimation","date":"2025-05-28","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/ragppi-rag-benchmark-for-protein-protein","slug":"ragppi-rag-benchmark-for-protein-protein","title":"RAGPPI: RAG Benchmark for Protein-Protein Interactions in Drug Discovery","date":"2025-05-28","arxiv_id":"2505.23823","n_code_links":1,"syntology":null},{"paper":null,"slug":"security-benefits-and-side-effects-of","title":"Security Benefits and Side Effects of Labeling AI-Generated Images","date":"2025-05-28","arxiv_id":"2505.22845","n_code_links":0,"syntology":null},{"paper":null,"slug":"shtocc-effective-3d-occupancy-prediction-with","title":"SHTOcc: Effective 3D Occupancy Prediction with Sparse Head and Tail Voxels","date":"2025-05-28","arxiv_id":"2505.22461","n_code_links":0,"syntology":null},{"paper":"/paper/talent-or-luck-evaluating-attribution-bias-in","slug":"talent-or-luck-evaluating-attribution-bias-in","title":"Talent or Luck? Evaluating Attribution Bias in Large Language Models","date":"2025-05-28","arxiv_id":"2505.22910","n_code_links":1,"syntology":null},{"paper":null,"slug":"targeted-unlearning-using-perturbed-sign","title":"Targeted Unlearning Using Perturbed Sign Gradient Methods With Applications On Medical Images","date":"2025-05-28","arxiv_id":"2505.21872","n_code_links":0,"syntology":null},{"paper":null,"slug":"topological-structure-learning-should-be-a","title":"Topological Structure Learning Should Be A Research Priority for LLM-Based Multi-Agent Systems","date":"2025-05-28","arxiv_id":"2505.22467","n_code_links":0,"syntology":null},{"paper":null,"slug":"understanding-adversarial-training-with","title":"Understanding Adversarial Training with Energy-based Models","date":"2025-05-28","arxiv_id":"2505.22486","n_code_links":0,"syntology":null},{"paper":null,"slug":"valuesim-generating-backstories-to-model","title":"ValueSim: Generating Backstories to Model Individual Value Systems","date":"2025-05-28","arxiv_id":"2505.23827","n_code_links":0,"syntology":null},{"paper":"/paper/vignette-socially-grounded-bias-evaluation","slug":"vignette-socially-grounded-bias-evaluation","title":"VIGNETTE: Socially Grounded Bias Evaluation for Vision-Language Models","date":"2025-05-28","arxiv_id":"2505.22897","n_code_links":1,"syntology":null},{"paper":"/paper/vme-a-satellite-imagery-dataset-and-benchmark","slug":"vme-a-satellite-imagery-dataset-and-benchmark","title":"VME: A Satellite Imagery Dataset and Benchmark for Detecting Vehicles in the Middle East and Beyond","date":"2025-05-28","arxiv_id":"2505.22353","n_code_links":1,"syntology":null},{"paper":null,"slug":"voice-cms-updating-the-knowledge-base-of-a","title":"Voice CMS: updating the knowledge base of a digital assistant through conversation","date":"2025-05-28","arxiv_id":"2505.22303","n_code_links":0,"syntology":null},{"paper":null,"slug":"backtrackagent-enhancing-gui-agent-with-error","title":"BacktrackAgent: Enhancing GUI Agent with Error Detection and Backtracking Mechanism","date":"2025-05-27","arxiv_id":"2505.20660","n_code_links":0,"syntology":null},{"paper":"/paper/bencher-simple-and-reproducible-benchmarking","slug":"bencher-simple-and-reproducible-benchmarking","title":"Bencher: Simple and Reproducible Benchmarking for Black-Box Optimization","date":"2025-05-27","arxiv_id":"2505.21321","n_code_links":1,"syntology":null},{"paper":null,"slug":"beyond-chemical-qa-evaluating-llm-s-chemical","title":"Beyond Chemical QA: Evaluating LLM's Chemical Reasoning with Modular Chemical Operations","date":"2025-05-27","arxiv_id":"2505.21318","n_code_links":0,"syntology":null},{"paper":null,"slug":"boosting-adversarial-transferability-via-high","title":"Boosting Adversarial Transferability via High-Frequency Augmentation and Hierarchical-Gradient Fusion","date":"2025-05-27","arxiv_id":"2505.21181","n_code_links":0,"syntology":null},{"paper":"/paper/cognibench-a-legal-inspired-framework-and","slug":"cognibench-a-legal-inspired-framework-and","title":"CogniBench: A Legal-inspired Framework and Dataset for Assessing Cognitive Faithfulness of Large Language Models","date":"2025-05-27","arxiv_id":"2505.20767","n_code_links":1,"syntology":null},{"paper":null,"slug":"creativity-in-llm-based-multi-agent-systems-a","title":"Creativity in LLM-based Multi-Agent Systems: A Survey","date":"2025-05-27","arxiv_id":"2505.21116","n_code_links":0,"syntology":null},{"paper":"/paper/dlp-dynamic-layerwise-pruning-in-large","slug":"dlp-dynamic-layerwise-pruning-in-large","title":"DLP: Dynamic Layerwise Pruning in Large Language Models","date":"2025-05-27","arxiv_id":"2505.23807","n_code_links":1,"syntology":{"ran":0,"of":10,"n_ran_checked":0,"n_instrument":0,"unverified":10,"pointer_only":0,"phrase":"0 ran · 10 unverified","official":{"repos":["ironartisan/dlp"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":10,"ran_from_kinds":[]}}},{"paper":"/paper/evaluating-llm-adaptation-to-sociodemographic","slug":"evaluating-llm-adaptation-to-sociodemographic","title":"Evaluating LLM Adaptation to Sociodemographic Factors: User Profile vs. Dialogue History","date":"2025-05-27","arxiv_id":"2505.21362","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["FerdinandZhong/model_behavior_adaption"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/fintagging-an-llm-ready-benchmark-for","slug":"fintagging-an-llm-ready-benchmark-for","title":"FinTagging: An LLM-ready Benchmark for Extracting and Structuring Financial Information","date":"2025-05-27","arxiv_id":"2505.20650","n_code_links":1,"syntology":null},{"paper":null,"slug":"humble-ai-in-the-real-world-the-case-of","title":"Humble AI in the real-world: the case of algorithmic hiring","date":"2025-05-27","arxiv_id":"2505.20918","n_code_links":0,"syntology":null},{"paper":null,"slug":"llms-think-but-not-in-your-flow-reasoning","title":"LLMs Think, But Not In Your Flow: Reasoning-Level Personalization for Black-Box Large Language Models","date":"2025-05-27","arxiv_id":"2505.21082","n_code_links":0,"syntology":null},{"paper":null,"slug":"loquacious-set-25000-hours-of-transcribed-and","title":"Loquacious Set: 25,000 Hours of Transcribed and Diverse English Speech Recognition Data for Research and Commercial Use","date":"2025-05-27","arxiv_id":"2505.21578","n_code_links":0,"syntology":null},{"paper":null,"slug":"melodysim-measuring-melody-aware-music","title":"MelodySim: Measuring Melody-aware Music Similarity for Plagiarism Detection","date":"2025-05-27","arxiv_id":"2505.20979","n_code_links":0,"syntology":null},{"paper":null,"slug":"mitigating-hallucination-in-large-vision","title":"Mitigating Hallucination in Large Vision-Language Models via Adaptive Attention Calibration","date":"2025-05-27","arxiv_id":"2505.21472","n_code_links":0,"syntology":null},{"paper":null,"slug":"moe-gyro-self-supervised-over-range","title":"MoE-Gyro: Self-Supervised Over-Range Reconstruction and Denoising for MEMS Gyroscopes","date":"2025-05-27","arxiv_id":"2506.06318","n_code_links":0,"syntology":null},{"paper":null,"slug":"output-regulation-of-linear-systems-with-non","title":"Output Regulation of Linear Systems with Non-periodic Non-smooth Exogenous Signals","date":"2025-05-27","arxiv_id":"2505.21209","n_code_links":0,"syntology":null},{"paper":null,"slug":"private-differentially-private-confidence","title":"PrivATE: Differentially Private Confidence Intervals for Average Treatment Effects","date":"2025-05-27","arxiv_id":"2505.21641","n_code_links":0,"syntology":null},{"paper":null,"slug":"sosbench-benchmarking-safety-alignment-on","title":"SOSBENCH: Benchmarking Safety Alignment on Scientific Knowledge","date":"2025-05-27","arxiv_id":"2505.21605","n_code_links":0,"syntology":null},{"paper":null,"slug":"walk-before-you-run-concise-llm-reasoning-via","title":"Walk Before You Run! Concise LLM Reasoning via Reinforcement Learning","date":"2025-05-27","arxiv_id":"2505.21178","n_code_links":0,"syntology":null},{"paper":null,"slug":"adaptive-location-hierarchy-learning-for-long","title":"Adaptive Location Hierarchy Learning for Long-Tailed Mobility Prediction","date":"2025-05-26","arxiv_id":"2505.19965","n_code_links":0,"syntology":null},{"paper":null,"slug":"adatp-attention-debiased-token-pruning-for","title":"AdaTP: Attention-Debiased Token Pruning for Video Large Language Models","date":"2025-05-26","arxiv_id":"2505.20100","n_code_links":0,"syntology":null},{"paper":"/paper/benchmarking-multimodal-knowledge-conflict","slug":"benchmarking-multimodal-knowledge-conflict","title":"Benchmarking Multimodal Knowledge Conflict for Large Multimodal Models","date":"2025-05-26","arxiv_id":"2505.19509","n_code_links":1,"syntology":null},{"paper":null,"slug":"bridging-the-long-term-gap-a-memory-active","title":"Bridging the Long-Term Gap: A Memory-Active Policy for Multi-Session Task-Oriented Dialogue","date":"2025-05-26","arxiv_id":"2505.20231","n_code_links":0,"syntology":null},{"paper":"/paper/calibrating-pre-trained-language-classifiers","slug":"calibrating-pre-trained-language-classifiers","title":"Calibrating Pre-trained Language Classifiers on LLM-generated Noisy Labels via Iterative Refinement","date":"2025-05-26","arxiv_id":"2505.19675","n_code_links":1,"syntology":null},{"paper":"/paper/can-compressed-llms-truly-act-an-empirical","slug":"can-compressed-llms-truly-act-an-empirical","title":"Can Compressed LLMs Truly Act? An Empirical Evaluation of Agentic Capabilities in LLM Compression","date":"2025-05-26","arxiv_id":"2505.19433","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":3,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["pprp/acbench"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"paper":null,"slug":"catoni-style-change-point-detection-for","title":"Catoni-Style Change Point Detection for Regret Minimization in Non-Stationary Heavy-Tailed Bandits","date":"2025-05-26","arxiv_id":"2505.20051","n_code_links":0,"syntology":null},{"paper":"/paper/chain-of-thought-for-autonomous-driving-a","slug":"chain-of-thought-for-autonomous-driving-a","title":"Chain-of-Thought for Autonomous Driving: A Comprehensive Survey and Future Prospects","date":"2025-05-26","arxiv_id":"2505.20223","n_code_links":1,"syntology":null},{"paper":null,"slug":"cotguard-using-chain-of-thought-triggering","title":"CoTGuard: Using Chain-of-Thought Triggering for Copyright Protection in Multi-Agent LLM Systems","date":"2025-05-26","arxiv_id":"2505.19405","n_code_links":0,"syntology":null},{"paper":null,"slug":"data-dependent-regret-bounds-for-constrained","title":"Data-Dependent Regret Bounds for Constrained MABs","date":"2025-05-26","arxiv_id":"2505.20010","n_code_links":0,"syntology":null},{"paper":"/paper/data-free-class-incremental-gesture-1","slug":"data-free-class-incremental-gesture-1","title":"Data-Free Class-Incremental Gesture Recognition with Prototype-Guided Pseudo Feature Replay","date":"2025-05-26","arxiv_id":"2505.20049","n_code_links":1,"syntology":null},{"paper":null,"slug":"decomposing-complex-visual-comprehension-into","title":"Decomposing Complex Visual Comprehension into Atomic Visual Skills for Vision Language Models","date":"2025-05-26","arxiv_id":"2505.20021","n_code_links":0,"syntology":null},{"paper":null,"slug":"effectiveness-of-prompt-optimization-in","title":"Effectiveness of Prompt Optimization in NL2SQL Systems","date":"2025-05-26","arxiv_id":"2505.20591","n_code_links":0,"syntology":null},{"paper":null,"slug":"energy-based-preference-optimization-for-test","title":"Energy-based Preference Optimization for Test-time Adaptation","date":"2025-05-26","arxiv_id":"2505.19607","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-contrastive-learning-based","slug":"enhancing-contrastive-learning-based","title":"Enhancing Contrastive Learning-based Electrocardiogram Pretrained Model with Patient Memory Queue","date":"2025-05-26","arxiv_id":"2506.06310","n_code_links":1,"syntology":null},{"paper":null,"slug":"fairness-practices-in-industry-a-case-study","title":"Fairness Practices in Industry: A Case Study in Machine Learning Teams Building Recommender Systems","date":"2025-05-26","arxiv_id":"2505.19441","n_code_links":0,"syntology":null},{"paper":"/paper/from-what-to-how-attributing-clip-s-latent","slug":"from-what-to-how-attributing-clip-s-latent","title":"From What to How: Attributing CLIP's Latent Components Reveals Unexpected Semantic Reliance","date":"2025-05-26","arxiv_id":"2505.20229","n_code_links":1,"syntology":null},{"paper":"/paper/gec-metrics-a-unified-library-for-grammatical","slug":"gec-metrics-a-unified-library-for-grammatical","title":"gec-metrics: A Unified Library for Grammatical Error Correction Evaluation","date":"2025-05-26","arxiv_id":"2505.19388","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["gotutiyan/gec-metrics-app"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"guard-me-if-you-know-me-protecting-specific","title":"Guard Me If You Know Me: Protecting Specific Face-Identity from Deepfakes","date":"2025-05-26","arxiv_id":"2505.19582","n_code_links":0,"syntology":null},{"paper":"/paper/haodiff-human-aware-one-step-diffusion-via","slug":"haodiff-human-aware-one-step-diffusion-via","title":"HAODiff: Human-Aware One-Step Diffusion via Dual-Prompt Guidance","date":"2025-05-26","arxiv_id":"2505.19742","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["gobunu/haodiff"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/homebench-evaluating-llms-in-smart-homes-with","slug":"homebench-evaluating-llms-in-smart-homes-with","title":"HomeBench: Evaluating LLMs in Smart Homes with Valid and Invalid Instructions Across Single and Multiple Devices","date":"2025-05-26","arxiv_id":"2505.19628","n_code_links":1,"syntology":null},{"paper":"/paper/infocons-identifying-interpretable-critical","slug":"infocons-identifying-interpretable-critical","title":"InfoCons: Identifying Interpretable Critical Concepts in Point Clouds via Information Theory","date":"2025-05-26","arxiv_id":"2505.19820","n_code_links":1,"syntology":{"ran":3,"of":7,"n_ran_checked":2,"n_instrument":1,"unverified":4,"pointer_only":7,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","official":{"repos":["llffff/infocons-pc"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/k-buffers-a-plug-in-method-for-enhancing","slug":"k-buffers-a-plug-in-method-for-enhancing","title":"K-Buffers: A Plug-in Method for Enhancing Neural Fields with Multiple Buffers","date":"2025-05-26","arxiv_id":"2505.19564","n_code_links":1,"syntology":null},{"paper":null,"slug":"knowledge-aligned-counterfactual-enhancement","title":"Knowledge-Aligned Counterfactual-Enhancement Diffusion Perception for Unsupervised Cross-Domain Visual Emotion Recognition","date":"2025-05-26","arxiv_id":"2505.19694","n_code_links":0,"syntology":null},{"paper":"/paper/lego-sketch-a-scalable-memory-augmented","slug":"lego-sketch-a-scalable-memory-augmented","title":"Lego Sketch: A Scalable Memory-augmented Neural Network for Sketching Data Streams","date":"2025-05-26","arxiv_id":"2505.19561","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["ffy0/legosketch_icml"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":"/paper/lifelong-safety-alignment-for-language-models","slug":"lifelong-safety-alignment-for-language-models","title":"Lifelong Safety Alignment for Language Models","date":"2025-05-26","arxiv_id":"2505.20259","n_code_links":1,"syntology":null},{"paper":"/paper/memory-efficient-visual-autoregressive","slug":"memory-efficient-visual-autoregressive","title":"Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression","date":"2025-05-26","arxiv_id":"2505.19602","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 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; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["stargazerx0/scalekv"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/mineanybuild-benchmarking-spatial-planning","slug":"mineanybuild-benchmarking-spatial-planning","title":"MineAnyBuild: Benchmarking Spatial Planning for Open-world AI Agents","date":"2025-05-26","arxiv_id":"2505.20148","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["mineanybuild/mineanybuild"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"paper":null,"slug":"my-answer-is-not-fair-mitigating-social-bias","title":"My Answer Is NOT 'Fair': Mitigating Social Bias in Vision-Language Models via Fair and Biased Residuals","date":"2025-05-26","arxiv_id":"2505.23798","n_code_links":0,"syntology":null},{"paper":"/paper/omnicharacter-towards-immersive-role-playing","slug":"omnicharacter-towards-immersive-role-playing","title":"OmniCharacter: Towards Immersive Role-Playing Agents with Seamless Speech-Language Personality Interaction","date":"2025-05-26","arxiv_id":"2505.20277","n_code_links":1,"syntology":null},{"paper":null,"slug":"reasoning-is-not-all-you-need-examining-llms","title":"Reasoning Is Not All You Need: Examining LLMs for Multi-Turn Mental Health Conversations","date":"2025-05-26","arxiv_id":"2505.20201","n_code_links":0,"syntology":null},{"paper":"/paper/rethinking-text-based-protein-understanding","slug":"rethinking-text-based-protein-understanding","title":"Rethinking Text-based Protein Understanding: Retrieval or LLM?","date":"2025-05-26","arxiv_id":"2505.20354","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["IDEA-XL/RAPM"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/select-read-and-write-a-multi-agent-framework","slug":"select-read-and-write-a-multi-agent-framework","title":"Select, Read, and Write: A Multi-Agent Framework of Full-Text-based Related Work Generation","date":"2025-05-26","arxiv_id":"2505.19647","n_code_links":1,"syntology":null},{"paper":null,"slug":"sgm-a-framework-for-building-specification","title":"SGM: A Framework for Building Specification-Guided Moderation Filters","date":"2025-05-26","arxiv_id":"2505.19766","n_code_links":0,"syntology":null},{"paper":"/paper/tailorkv-a-hybrid-framework-for-long-context","slug":"tailorkv-a-hybrid-framework-for-long-context","title":"TailorKV: A Hybrid Framework for Long-Context Inference via Tailored KV Cache Optimization","date":"2025-05-26","arxiv_id":"2505.19586","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-role-of-diversity-in-in-context-learning","title":"The Role of Diversity in In-Context Learning for Large Language Models","date":"2025-05-26","arxiv_id":"2505.19426","n_code_links":0,"syntology":null},{"paper":"/paper/translation-equivariance-of-normalization","slug":"translation-equivariance-of-normalization","title":"Translation-Equivariance of Normalization Layers and Aliasing in Convolutional Neural Networks","date":"2025-05-26","arxiv_id":"2505.19805","n_code_links":1,"syntology":null},{"paper":"/paper/tuna-comprehensive-fine-grained-temporal","slug":"tuna-comprehensive-fine-grained-temporal","title":"TUNA: Comprehensive Fine-grained Temporal Understanding Evaluation on Dense Dynamic Videos","date":"2025-05-26","arxiv_id":"2505.20124","n_code_links":1,"syntology":null},{"paper":null,"slug":"uniform-convergence-of-the-smooth-calibration","title":"Uniform convergence of the smooth calibration error and its relationship with functional gradient","date":"2025-05-26","arxiv_id":"2505.19396","n_code_links":0,"syntology":null},{"paper":"/paper/unlocking-the-power-of-diffusion-models-in","slug":"unlocking-the-power-of-diffusion-models-in","title":"Unlocking the Power of Diffusion Models in Sequential Recommendation: A Simple and Effective Approach","date":"2025-05-26","arxiv_id":"2505.19544","n_code_links":1,"syntology":null},{"paper":"/paper/visual-abstract-thinking-empowers-multimodal","slug":"visual-abstract-thinking-empowers-multimodal","title":"Visual Abstract Thinking Empowers Multimodal Reasoning","date":"2025-05-26","arxiv_id":"2505.20164","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-comprehensive-survey-on-the-risks-and","title":"A Comprehensive Survey on the Risks and Limitations of Concept-based Models","date":"2025-05-25","arxiv_id":"2506.04237","n_code_links":0,"syntology":null},{"paper":"/paper/a-graph-perspective-to-probe-structural","slug":"a-graph-perspective-to-probe-structural","title":"A Graph Perspective to Probe Structural Patterns of Knowledge in Large Language Models","date":"2025-05-25","arxiv_id":"2505.19286","n_code_links":1,"syntology":null},{"paper":"/paper/bnmmlu-measuring-massive-multitask-language","slug":"bnmmlu-measuring-massive-multitask-language","title":"BnMMLU: Measuring Massive Multitask Language Understanding in Bengali","date":"2025-05-25","arxiv_id":"2505.18951","n_code_links":1,"syntology":null},{"paper":null,"slug":"broadgen-a-framework-for-generating-effective","title":"BroadGen: A Framework for Generating Effective and Efficient Advertiser Broad Match Keyphrase Recommendations","date":"2025-05-25","arxiv_id":"2505.19164","n_code_links":0,"syntology":null},{"paper":"/paper/can-multimodal-large-language-models","slug":"can-multimodal-large-language-models","title":"Can Multimodal Large Language Models Understand Spatial Relations?","date":"2025-05-25","arxiv_id":"2505.19015","n_code_links":1,"syntology":{"ran":2,"of":5,"n_ran_checked":2,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["ziyan-xiaoyu/spatialmqa"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"cardiocot-hierarchical-reasoning-for","title":"CardioCoT: Hierarchical Reasoning for Multimodal Survival Analysis","date":"2025-05-25","arxiv_id":"2505.19195","n_code_links":0,"syntology":null},{"paper":"/paper/chartsketcher-reasoning-with-multimodal","slug":"chartsketcher-reasoning-with-multimodal","title":"ChartSketcher: Reasoning with Multimodal Feedback and Reflection for Chart Understanding","date":"2025-05-25","arxiv_id":"2505.19076","n_code_links":1,"syntology":null},{"paper":"/paper/chi-square-wavelet-graph-neural-networks-for","slug":"chi-square-wavelet-graph-neural-networks-for","title":"Chi-Square Wavelet Graph Neural Networks for Heterogeneous Graph Anomaly Detection","date":"2025-05-25","arxiv_id":"2505.18934","n_code_links":1,"syntology":null},{"paper":"/paper/demand-selection-for-vrp-with-emission-quota","slug":"demand-selection-for-vrp-with-emission-quota","title":"Demand Selection for VRP with Emission Quota","date":"2025-05-25","arxiv_id":"2505.19315","n_code_links":1,"syntology":null},{"paper":null,"slug":"estimating-online-influence-needs-causal","title":"Estimating Online Influence Needs Causal Modeling! Counterfactual Analysis of Social Media Engagement","date":"2025-05-25","arxiv_id":"2505.19355","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-steering-techniques-using-human","title":"Evaluating Steering Techniques using Human Similarity Judgments","date":"2025-05-25","arxiv_id":"2505.19333","n_code_links":0,"syntology":null},{"paper":null,"slug":"federated-learning-from-theory-to-practice","title":"Federated Learning: From Theory to Practice","date":"2025-05-25","arxiv_id":"2505.19183","n_code_links":0,"syntology":null},{"paper":null,"slug":"gc-kbvqa-a-new-four-stage-framework-for","title":"GC-KBVQA: A New Four-Stage Framework for Enhancing Knowledge Based Visual Question Answering Performance","date":"2025-05-25","arxiv_id":"2505.19354","n_code_links":0,"syntology":null},{"paper":null,"slug":"geometric-determinations-of-characteristic","title":"Geometric Determinations Of Characteristic Redshifts From DESI-DR2 BAO and DES-SN5YR Observations: Hints For New Expansion Rate Anomalies","date":"2025-05-25","arxiv_id":"2505.19083","n_code_links":0,"syntology":null}],"record_sha256":"162f467b37229f60be72336306020904c585fea40a585da935b0c2583102eebd","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}