{"total":32,"items":[{"citing_arxiv_id":"2605.22995","ref_index":155,"ref_count":1,"confidence":0.35,"is_internal_anchor":false,"paper_title":"Whose Good, Whose Place? The Moral Geography of Agentic AI for Social Good","primary_cat":"cs.CY","submitted_at":"2026-05-21T19:49:27+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Survey of 112 agentic AI for social good papers reveals moral-geographic asymmetry with 73% lacking geographic context (lowest for SDG 16) and only 25% reporting deployments.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.21609","ref_index":9,"ref_count":1,"confidence":0.35,"is_internal_anchor":false,"paper_title":"CR4T: Rewrite-Based Guardrails for Adolescent LLM Safety","primary_cat":"cs.CL","submitted_at":"2026-05-20T18:16:18+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"CR4T is a model-agnostic framework using lightweight risk detection and domain-conditioned rewriting to convert unsafe or refusal-style LLM responses into developmentally appropriate guidance for adolescents.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.20646","ref_index":105,"ref_count":1,"confidence":0.35,"is_internal_anchor":false,"paper_title":"DisImpact: Quantifying the Physi-Social Impact of Natural Disasters Through Social Media","primary_cat":"cs.SI","submitted_at":"2026-05-20T03:09:21+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"DisImpact introduces a two-stage MLLM framework to classify disaster-related social media posts into ten impact categories and compute a unified physi-social impact index validated against FEMA and NASA ground-truth data.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.20347","ref_index":67,"ref_count":1,"confidence":0.35,"is_internal_anchor":false,"paper_title":"Symmetrization of Loss Functions for Robust Training of Neural Networks in the Presence of Noisy Labels","primary_cat":"cs.LG","submitted_at":"2026-05-19T18:03:40+00:00","verdict":null,"verdict_confidence":null,"novelty_score":null,"formal_verification":null,"one_line_summary":null,"context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.20128","ref_index":9,"ref_count":1,"confidence":0.35,"is_internal_anchor":false,"paper_title":"MixRea: Benchmarking Explicit-Implicit Reasoning in Large Language Models","primary_cat":"cs.CL","submitted_at":"2026-05-19T17:15:08+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"MixRea benchmark reveals LLMs achieve at most 42.8% consistency on explicit-implicit reasoning tasks, with PRCP prompting proposed to recover overlooked relations.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.19822","ref_index":9,"ref_count":1,"confidence":0.35,"is_internal_anchor":false,"paper_title":"ST-TGExplainer: Disentangling Stability and Transition Patterns for Temporal GNN Interpretability","primary_cat":"cs.LG","submitted_at":"2026-05-19T13:16:22+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"ST-TGExplainer disentangles stability and transition patterns in temporal graphs via a self-explainable TGNN guided by a disentangled information bottleneck objective to produce more faithful explanations.","context_count":1,"top_context_role":"method","top_context_polarity":"use_method","context_text":"The function φ(·) is a trainable mapping that transforms relative times into a dR- dimensional space, enabling the model to encode the recent activity patterns of both source and destination nodes. We then concatenate all feature components and project them through an MLP to obtain the unified feature sequence: Z(0) = MLP [Xt N ,X t E,X t T ,X t R] \u0001 ∈R L×d.(9) To model structural and temporal dependencies, we apply l stacked layers of MLP-Mixer (Tolstikhin et al., 2021). Each layer updates the representation as follows: ˜Z(l) =Z (l−1) +W (l) 1 GeLU \u0010 W(l) 2 LN \u0010 Z(l−1) \u0011\u0011 , Z(l) = ˜Z(l) +W (l) 3 GeLU \u0010 W(l) 4 LN \u0010 ˜Z(l) \u0011\u0011 , (10) where GeLU is the activation function, LN denotes layer normalization, and W(l)"},{"citing_arxiv_id":"2605.19316","ref_index":99,"ref_count":1,"confidence":0.35,"is_internal_anchor":false,"paper_title":"A Multi-Agent Framework for Feature-Constrained Difficulty Control in Reading Comprehension Item Generation","primary_cat":"cs.CL","submitted_at":"2026-05-19T03:52:00+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"MAFIG is a multi-agent framework that uses LLM agents and evaluators to generate reading comprehension items with significantly higher adherence to specified feature constraints than single-agent baselines.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.18246","ref_index":88,"ref_count":1,"confidence":0.35,"is_internal_anchor":false,"paper_title":"Privacy Preserving Reinforcement Learning with One-Sided Feedback","primary_cat":"cs.LG","submitted_at":"2026-05-18T11:41:03+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"POOL is a new RL algorithm that adds privacy protection in continuous spaces with one-sided feedback and achieves sample complexity matching known non-private lower bounds.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.18111","ref_index":9,"ref_count":1,"confidence":0.35,"is_internal_anchor":false,"paper_title":"How Good LLMs Are at Answering Bangla Medical Visual Questions? Dataset and Benchmarking","primary_cat":"cs.CL","submitted_at":"2026-05-18T09:20:32+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Introduces BanglaMedVQA dataset of clinically validated image-question-answer pairs and benchmarks foundation models, finding substantially lower performance than on English MedVQA especially on diagnostic questions.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.17270","ref_index":285,"ref_count":1,"confidence":0.35,"is_internal_anchor":false,"paper_title":"Beyond Detection: A Structure-Aware Framework for Scene Text Tracking","primary_cat":"cs.CV","submitted_at":"2026-05-17T05:40:55+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"SymTrack is the first systematic detection-free framework for scene text tracking that constructs benchmarks from video text spotting datasets and reports up to 11.97% AUC gains over prior trackers.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.15253","ref_index":9,"ref_count":1,"confidence":0.35,"is_internal_anchor":false,"paper_title":"Position: Ideas Should be the Center of Machine Learning Research","primary_cat":"cs.LG","submitted_at":"2026-05-14T16:36:27+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Machine learning research should prioritize ideas by testing their predicted behavioral signatures in modern models through custom experiments instead of leaderboard chasing or abstract theorems.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.13233","ref_index":88,"ref_count":1,"confidence":0.35,"is_internal_anchor":false,"paper_title":"Doppler Prompting for Stable mmWave-based Human Pose Estimation","primary_cat":"cs.HC","submitted_at":"2026-05-13T09:24:11+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"PULSE stabilizes mmWave human pose estimation by screening Doppler motion prompts before injecting them into spatial magnitude reasoning.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.12981","ref_index":36,"ref_count":2,"confidence":0.35,"is_internal_anchor":false,"paper_title":"Protocol-Driven Development: Governing Generated Software Through Invariants and Continuous Evidence","primary_cat":"cs.SE","submitted_at":"2026-05-13T04:23:14+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"The paper introduces Protocol-Driven Development as a governance model for automated software engineering centered on machine-enforceable protocols, evidence chains, and dynamic runtime ledgers.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.09922","ref_index":9,"ref_count":1,"confidence":0.35,"is_internal_anchor":false,"paper_title":"Team-Based Self-Play With Dual Adaptive Weighting for Fine-Tuning LLMs","primary_cat":"cs.CL","submitted_at":"2026-05-11T03:17:31+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"TPAW uses teams of current and historical model checkpoints that collaborate and compete, plus adaptive weightings for responses and players, to improve self-supervised LLM alignment and outperform baselines.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.06999","ref_index":26,"ref_count":1,"confidence":0.35,"is_internal_anchor":false,"paper_title":"TubeCensus: A Transparent, Replicable, and Large-Scale Census of YouTube Channels and their Subscriber Counts Over Time","primary_cat":"cs.SI","submitted_at":"2026-05-07T22:30:51+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"TubeCensus provides a transparent longitudinal dataset of YouTube channels and subscriber counts covering creators responsible for 30-36% of platform content, distributed via a pip package.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.04641","ref_index":17,"ref_count":1,"confidence":0.35,"is_internal_anchor":false,"paper_title":"CAST: Mitigating Object Hallucination in Large Vision-Language Models via Caption-Guided Visual Attention Steering","primary_cat":"cs.CV","submitted_at":"2026-05-06T08:32:30+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"CAST reduces object hallucination in LVLMs by 6.03% on average across five models and five benchmarks by identifying caption-sensitive attention heads and applying optimized steering directions to their outputs, with negligible added inference cost.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.02780","ref_index":14,"ref_count":1,"confidence":0.35,"is_internal_anchor":false,"paper_title":"Fine-Grained Graph Generation through Latent Mixture Scheduling","primary_cat":"cs.AI","submitted_at":"2026-05-04T16:23:01+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"A novel CVAE with mixture scheduling achieves fine-grained structural control in graph generation, showing high quality and controllability on five datasets.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.02640","ref_index":148,"ref_count":1,"confidence":0.35,"is_internal_anchor":false,"paper_title":"Trustworthy AI Suffers from Invariance Conflicts and Causality is The Solution","primary_cat":"cs.AI","submitted_at":"2026-05-04T14:26:28+00:00","verdict":null,"verdict_confidence":null,"novelty_score":null,"formal_verification":null,"one_line_summary":null,"context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.00578","ref_index":35,"ref_count":1,"confidence":0.35,"is_internal_anchor":false,"paper_title":"Federated Distillation for Whole Slide Image via Gaussian-Mixture Feature Alignment and Curriculum Integration","primary_cat":"cs.CV","submitted_at":"2026-05-01T11:25:54+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"FedHD is a federated learning framework for whole slide images that distills one-to-one synthetic features aligned via Gaussian mixtures and progressively integrates cross-site features through curriculum learning to handle institutional heterogeneity.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.08111","ref_index":12,"ref_count":1,"confidence":0.35,"is_internal_anchor":false,"paper_title":"TTCD:Transformer Integrated Temporal Causal Discovery from Non-Stationary Time Series Data","primary_cat":"cs.LG","submitted_at":"2026-04-27T19:44:38+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"TTCD uses a non-stationary feature learner and reconstruction-guided distillation inside a transformer to infer contemporaneous and lagged causal graphs from non-stationary time series without strong noise assumptions.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"Satoshi Endo, Ann M Fridlind, Wuyin Lin, Andrew M V ogelmann, Tami Toto, Andrew S Ackerman, Greg M McFarquhar, Robert C Jackson, Haflidi H Jonsson, and Yangang Liu. Racoro continental boundary layer cloud investigations: 2. large-eddy simulations of cumulus clouds and evaluation with in situ and ground-based observations.Journal of Geophysical Research: Atmospheres, 120 (12):5993-6014, 2015. Doris Entner and Patrik O Hoyer. On causal discovery from time series data using fci.Probabilistic graphical models, pp. 121-128, 2010. Muhammad Hasan Ferdous, Uzma Hasan, and Md Osman Gani. Cdans: Temporal Causal Discovery from Autocorrelated and Non-Stationary Time Series Data. 2023. Daigo Fujiwara, Kazuki Koyama, Keisuke Kiritoshi, Tomomi Okawachi, Tomonori Izumitani, and"},{"citing_arxiv_id":"2604.21326","ref_index":9,"ref_count":1,"confidence":0.35,"is_internal_anchor":false,"paper_title":"MiMIC: Mitigating Visual Modality Collapse in Universal Multimodal Retrieval While Avoiding Semantic Misalignment","primary_cat":"cs.CV","submitted_at":"2026-04-23T06:29:42+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"MiMIC mitigates visual modality collapse and semantic misalignment in universal multimodal retrieval via fusion-in-decoder architecture and robust single-modality training.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.21268","ref_index":102,"ref_count":1,"confidence":0.35,"is_internal_anchor":false,"paper_title":"Measure Twice, Click Once: Co-evolving Proposer and Visual Critic via Reinforcement Learning for GUI Grounding","primary_cat":"cs.LG","submitted_at":"2026-04-23T04:23:31+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A co-evolving proposer-critic RL framework improves GUI grounding accuracy by letting the model critique its own proposals rendered on screenshots.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.21251","ref_index":14,"ref_count":1,"confidence":0.35,"is_internal_anchor":false,"paper_title":"CAP: Controllable Alignment Prompting for Unlearning in LLMs","primary_cat":"cs.LG","submitted_at":"2026-04-23T03:42:41+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"CAP is a reinforcement-learning-driven prompt optimization framework that suppresses target knowledge in LLMs while preserving general capabilities, enabling reversible unlearning without any parameter updates.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.19949","ref_index":16,"ref_count":1,"confidence":0.35,"is_internal_anchor":false,"paper_title":"Indic-CodecFake meets SATYAM: Towards Detecting Neural Audio Codec Synthesized Speech Deepfakes in Indic Languages","primary_cat":"eess.AS","submitted_at":"2026-04-21T19:54:54+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Introduces the Indic-CodecFake dataset for Indic codec deepfakes and SATYAM, a novel hyperbolic ALM that outperforms baselines through dual-stage semantic-prosodic fusion using Bhattacharya distance.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.19048","ref_index":9,"ref_count":1,"confidence":0.35,"is_internal_anchor":false,"paper_title":"SAMoRA: Semantic-Aware Mixture of LoRA Experts for Task-Adaptive Learning","primary_cat":"cs.CL","submitted_at":"2026-04-21T03:55:02+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"SAMoRA is a parameter-efficient fine-tuning framework that uses semantic-aware routing and task-adaptive scaling within a Mixture of LoRA Experts to improve multi-task performance and generalization over prior methods.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.18939","ref_index":146,"ref_count":1,"confidence":0.35,"is_internal_anchor":false,"paper_title":"TabEmb: Joint Semantic-Structure Embedding for Table Annotation","primary_cat":"cs.LG","submitted_at":"2026-04-21T00:25:49+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"TabEmb decouples LLM-based semantic column embeddings from graph-based structural modeling to produce joint representations that improve table annotation tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.18460","ref_index":27,"ref_count":1,"confidence":0.35,"is_internal_anchor":false,"paper_title":"Learning Invariant Modality Representation for Robust Multimodal Learning from a Causal Inference Perspective","primary_cat":"cs.LG","submitted_at":"2026-04-20T16:16:36+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"CmIR uses causal inference to separate invariant causal representations from spurious ones in multimodal data, improving generalization under distribution shifts and noise via invariance, mutual information, and reconstruction constraints.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.17959","ref_index":9,"ref_count":1,"confidence":0.35,"is_internal_anchor":false,"paper_title":"Chatting about Upper-Body Expressive Human Pose and Shape Estimation","primary_cat":"cs.CV","submitted_at":"2026-04-20T08:40:54+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"CoEvoer is a new cross-dependency transformer framework for upper-body expressive human pose and shape estimation that achieves state-of-the-art performance by enabling mutual enhancement between body parts.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.17419","ref_index":9,"ref_count":1,"confidence":0.35,"is_internal_anchor":false,"paper_title":"ARMove: Learning to Predict Human Mobility through Agentic Reasoning","primary_cat":"cs.MA","submitted_at":"2026-04-19T12:59:20+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"ARMove is a transferable framework for human mobility prediction that combines agentic LLM reasoning, feature management, and large-small model synergy to outperform baselines on several metrics while improving interpretability and robustness.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.17407","ref_index":16,"ref_count":1,"confidence":0.35,"is_internal_anchor":false,"paper_title":"Think before Go: Hierarchical Reasoning for Image-goal Navigation","primary_cat":"cs.RO","submitted_at":"2026-04-19T12:30:22+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"HRNav decomposes image-goal navigation into VLM-based short-horizon planning and RL-based execution with a wandering suppression penalty to improve performance in complex unseen settings.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.17340","ref_index":9,"ref_count":1,"confidence":0.35,"is_internal_anchor":false,"paper_title":"Neuro-Symbolic Resolution of Recommendation Conflicts in Multimorbidity Clinical Guidelines","primary_cat":"cs.CL","submitted_at":"2026-04-19T09:22:17+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Neuro-symbolic pipeline using multi-agent translation and SAT solving detects conflicts in multimorbidity guidelines with 0.861 F1, finding 90.6% are local conflicts on 12 SGLT2 guidelines.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2309.08532","ref_index":85,"ref_count":1,"confidence":0.35,"is_internal_anchor":false,"paper_title":"EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizers","primary_cat":"cs.CL","submitted_at":"2023-09-15T16:50:09+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"EvoPrompt uses LLMs to run evolutionary operators on populations of prompts, outperforming human-engineered prompts by up to 25% on BIG-Bench Hard tasks across 31 datasets.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}