ρ-NPTS_SG is asymptotically optimal for continuous risk functionals on bounded-density sub-Gaussian distributions, with the first instance-optimal guarantees for non-Lipschitz cases like the Sharpe ratio.
hub Mixed citations
Clancey and Glenn Rennels , abstract =
Mixed citation behavior. Most common role is unclear (71%).
61
Pith papers citing it
71
external citations · Crossref
unclear
71% of classified citations
hub tools
citation-role summary
background 3
other 3
method 1
citation-polarity summary
representative citing papers
LLM evolutionary program synthesis learns domain-dependent admissible heuristics for optimal planning by generating pattern collections combined via saturated cost partitioning.
MVDGC unifies BEV and image-view pedestrian localization into one task via 3D cylindrical queries that enforce dual geometric constraints between views.
PS-PPO samples a per-trajectory cutoff and importance-weights truncated gradients, preserving the full critic-free update in expectation while cutting RLHF training compute and memory.
New cumulative natural direct and indirect effects are defined to decompose local causal effects into direct and indirect components for continuous and ordinal treatments while preserving skew-symmetry and additivity.
HDSL is a tree-structured DSL for 3D indoor scenes that lets LLM agents generate subtrees recursively and perform localized edits via hierarchical retrieval and deterministic merge.
A graph neural network with axial attention learns admissible cost partitions for planning heuristics by predicting weights that satisfy partition constraints by construction via Lagrangian dual equivalence.
P²-DPO generates on-policy preference pairs targeting focus-and-enhance perception and visual robustness, combined with a calibration loss, to reduce hallucinations in LVLMs more effectively than human-feedback baselines.
Fair fine-tuning under Equalized Odds yields a tight bound Adv(A, M_f) ≤ Δ_EO · W on adversarial advantage in distribution inference attacks, with empirical reductions below detection threshold across six datasets.
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.
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.
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.
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.
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.
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.
BUS trains VLMs for self-reflection without labels by verifying which sampled reasonings precede their own answers via backward prediction, improving multimodal reasoning.
Introduces the game changer problem and supplies feasibility characterizations plus dynamic programming algorithms for forcing a target equilibrium under discrete reward constraints in two-player games.
An edge-cloud pipeline that compresses long video into features, captions, and an entity graph answers streaming-video queries with 87.6% less bandwidth and near cloud-only accuracy.
Introduces Pareto C-optimality and PrefUCB algorithm for PDMOB with instance-dependent logarithmic regret bounds, validated on selective ensemble and asset allocation tasks.
BCL introduces a particle-filtering Bayesian update framework to systematically refine label representations in in-context learning for information extraction, claiming consistent gains over prior methods.
Trio proposes Temporal-Spatial-Sample attention and a TS-SCM synthetic data generator to improve multivariate time-series forecasting by reusing historical patterns and structural priors.
Graph Cascades uses contagion diffusion to rewire graphs by promoting reinforced multi-hop node pairs to direct neighbors, improving GNN performance on heterophilic and moderate-degree homophilic graphs under specified conditions.
Many LLMs exhibit stronger environmental cognition, affect, and behavioral recommendations than human survey averages and shift with persona prompts.
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.
citing papers explorer
-
Asymptotic Optimality of Thompson Sampling for Risk-Averse Bandits with Sub-Gaussian Rewards
ρ-NPTS_SG is asymptotically optimal for continuous risk functionals on bounded-density sub-Gaussian distributions, with the first instance-optimal guarantees for non-Lipschitz cases like the Sharpe ratio.
-
LLM-Evolved Pattern Generators for Optimal Classical Planning
LLM evolutionary program synthesis learns domain-dependent admissible heuristics for optimal planning by generating pattern collections combined via saturated cost partitioning.
-
MVDGC: Joint 3D and 2D Multi-view Pedestrian Detection via Dual Geometric Constraints
MVDGC unifies BEV and image-view pedestrian localization into one task via 3D cylindrical queries that enforce dual geometric constraints between views.
-
PS-PPO: Prefix-Sampling PPO for Critic-Free RLHF
PS-PPO samples a per-trajectory cutoff and importance-weights truncated gradients, preserving the full critic-free update in expectation while cutting RLHF training compute and memory.
-
Cumulative Natural Direct and Indirect Effects for Causal Mediation Analysis
New cumulative natural direct and indirect effects are defined to decompose local causal effects into direct and indirect components for continuous and ordinal treatments while preserving skew-symmetry and additivity.
-
HDSL: A Hierarchical Domain-Specific Language for Structured 3D Indoor Scene Generation and Localized Editing with LLM Agents
HDSL is a tree-structured DSL for 3D indoor scenes that lets LLM agents generate subtrees recursively and perform localized edits via hierarchical retrieval and deterministic merge.
-
Learning Admissible Heuristics via Cost Partitioning
A graph neural network with axial attention learns admissible cost partitions for planning heuristics by predicting weights that satisfy partition constraints by construction via Lagrangian dual equivalence.
-
P$^2$-DPO: Grounding Hallucination in Perceptual Processing via Calibration Direct Preference Optimization
P²-DPO generates on-policy preference pairs targeting focus-and-enhance perception and visual robustness, combined with a calibration loss, to reduce hallucinations in LVLMs more effectively than human-feedback baselines.
-
Fair Finetuning Mitigates Distribution Inference Attacks
Fair fine-tuning under Equalized Odds yields a tight bound Adv(A, M_f) ≤ Δ_EO · W on adversarial advantage in distribution inference attacks, with empirical reductions below detection threshold across six datasets.
-
Whose Good, Whose Place? The Moral Geography of Agentic AI for Social Good
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.
-
Beyond Detection: A Structure-Aware Framework for Scene Text Tracking
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.
-
Indic-CodecFake meets SATYAM: Towards Detecting Neural Audio Codec Synthesized Speech Deepfakes in Indic Languages
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.
-
Chatting about Upper-Body Expressive Human Pose and Shape Estimation
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.
-
Neuro-Symbolic Resolution of Recommendation Conflicts in Multimorbidity Clinical Guidelines
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.
-
EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizers
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.
-
BUS: Brain-Inspired Unsupervised Self-Reflection via Backward Prediction for Multimodal Reasoning
BUS trains VLMs for self-reflection without labels by verifying which sampled reasonings precede their own answers via backward prediction, improving multimodal reasoning.
-
The Game Changer Problem: Controlling Equilibria with Discrete Rewards
Introduces the game changer problem and supplies feasibility characterizations plus dynamic programming algorithms for forcing a target equilibrium under discrete reward constraints in two-player games.
-
CoVStream: Edge-Cloud Collaboration for Understanding of Long Video Streams
An edge-cloud pipeline that compresses long video into features, captions, and an entity graph answers streaming-video queries with 87.6% less bandwidth and near cloud-only accuracy.
-
Selective Ensemble Based on Preference-Directed Multi-Objective Bandits
Introduces Pareto C-optimality and PrefUCB algorithm for PDMOB with instance-dependent logarithmic regret bounds, validated on selective ensemble and asset allocation tasks.
-
BCL: Bayesian In-Context Learning Framework for Information Extraction
BCL introduces a particle-filtering Bayesian update framework to systematically refine label representations in in-context learning for information extraction, claiming consistent gains over prior methods.
-
Trio: Learning Time-Series Forecasting with Temporal-Spatial-Sample Attention and Structural Causal Priors
Trio proposes Temporal-Spatial-Sample attention and a TS-SCM synthetic data generator to improve multivariate time-series forecasting by reusing historical patterns and structural priors.
-
Graph Cascades: Contagion-Based Mesoscopic Rewiring for Structure-Aware Graph Machine Learning
Graph Cascades uses contagion diffusion to rewire graphs by promoting reinforced multi-hop node pairs to direct neighbors, improving GNN performance on heterophilic and moderate-degree homophilic graphs under specified conditions.
-
Greener Than Humans? Environmental Attitudes in Large Language Models
Many LLMs exhibit stronger environmental cognition, affect, and behavioral recommendations than human survey averages and shift with persona prompts.
-
DisImpact: Quantifying the Physi-Social Impact of Natural Disasters Through Social Media
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.
-
Symmetrization of Loss Functions for Robust Training of Neural Networks in the Presence of Noisy Labels
Symmetrizing cross-entropy produces the unique convex multi-class unhinged loss, which locally approximates other symmetric losses, and enables new interpolating losses SGCE and alpha-MAE with competitive performance on noisy-label benchmarks.
-
MixRea: Benchmarking Explicit-Implicit Reasoning in Large Language Models
MixRea benchmark reveals LLMs achieve at most 42.8% consistency on explicit-implicit reasoning tasks, with PRCP prompting proposed to recover overlooked relations.
-
ST-TGExplainer: Disentangling Stability and Transition Patterns for Temporal GNN Interpretability
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.
-
A Multi-Agent Framework for Feature-Constrained Difficulty Control in Reading Comprehension Item Generation
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.
-
How Good LLMs Are at Answering Bangla Medical Visual Questions? Dataset and Benchmarking
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.
-
Team-Based Self-Play With Dual Adaptive Weighting for Fine-Tuning LLMs
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.
-
TubeCensus: A Transparent, Replicable, and Large-Scale Census of YouTube Channels and their Subscriber Counts Over Time
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.
-
TTCD:Transformer Integrated Temporal Causal Discovery from Non-Stationary Time Series Data
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.
-
MiMIC: Mitigating Visual Modality Collapse in Universal Multimodal Retrieval While Avoiding Semantic Misalignment
MiMIC mitigates visual modality collapse and semantic misalignment in universal multimodal retrieval via fusion-in-decoder architecture and robust single-modality training.
-
CAP: Controllable Alignment Prompting for Unlearning in LLMs
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.
-
SAMoRA: Semantic-Aware Mixture of LoRA Experts for Task-Adaptive Learning
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.
-
When Can You Debias an LLM Judge? Identifiability Limits, a Test, and Designs for Top-k Ranking
A bias-aware Bradley-Terry judge cannot identify the quality/bias split from comparisons alone; only prior assumptions, trusted anchors, or paired renderings can supply it.
-
Enhancing Differentially Private Mechanisms via Empirical Bayes
Empirical Bayes denoising of Gaussian mechanism outputs reduces MSE for differentially private histogram release, PCA, and linear regression.
-
Shift-Dependent Asymmetry: Orthogonal Inverse Low-Rank Adaptation for Federated Medical Segmentation
Introduces IAT with module-specific personalization and orthogonality regularization to handle appearance and supervision shifts in federated medical segmentation.
-
IDO: Incongruity-aware Distribution Optimization for Multimodal Fake News Detection
IDO uses channel-wise reweighting, Gaussian modeling of factual uncertainty, and incongruity contrastive learning to achieve SOTA multimodal fake news detection.
-
Auditing Engagement Incentives in the Kidfluencer Ecosystem: A Multimodal Weak Supervision Approach
Multimodal weak-supervision audit finds exploitation signals in kidfluencer videos correlate with higher engagement, including a 4.4x view increase per unit exploitation score after channel controls.
-
When Meaning Travels: A Granular Lens on Hybrid-MoE's Role in Idiomatic Understanding for Language Models
HybridMoE with controlled hybridization and idiomatic property signals yields 5-6% gains in figurative language representation for multilingual vision-language models.
-
Richer Representations for Neural Algorithmic Reasoning via Auxiliary Reconstruction
Auxiliary reconstruction tasks improve encoder representations in neural algorithmic reasoning and raise performance on standard benchmarks.
-
CR4T: Rewrite-Based Guardrails for Adolescent LLM Safety
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.
-
Privacy Preserving Reinforcement Learning with One-Sided Feedback
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.
-
Doppler Prompting for Stable mmWave-based Human Pose Estimation
PULSE stabilizes mmWave human pose estimation by screening Doppler motion prompts before injecting them into spatial magnitude reasoning.
-
Protocol-Driven Development: Governing Generated Software Through Invariants and Continuous Evidence
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.
-
CAST: Mitigating Object Hallucination in Large Vision-Language Models via Caption-Guided Visual Attention Steering
A training-free method that steers specific attention heads toward caption-query states reduces object hallucination in LVLMs by ~6% on average across five benchmarks.
-
Measure Twice, Click Once: Co-evolving Proposer and Visual Critic via Reinforcement Learning for GUI Grounding
A co-evolving proposer-critic RL framework improves GUI grounding accuracy by letting the model critique its own proposals rendered on screenshots.
-
TabEmb: Joint Semantic-Structure Embedding for Table Annotation
TabEmb decouples LLM-based semantic column embeddings from graph-based structural modeling to produce joint representations that improve table annotation tasks.
-
Learning Invariant Modality Representation for Robust Multimodal Learning from a Causal Inference Perspective
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.