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.
hub
The Engineering of Qualitative Models
32 Pith papers cite this work. Polarity classification is still indexing.
32
Pith papers citing it
hub tools
citation-role summary
background 1
method 1
citation-polarity summary
representative citing papers
Symmetrization of multi-class losses produces a unique convex symmetric loss that locally approximates others and supports robust neural training under label noise.
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.
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.
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 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.
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.
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.
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 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.
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.
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 mitigates visual modality collapse and semantic misalignment in universal multimodal retrieval via fusion-in-decoder architecture and robust single-modality training.
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 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.
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.
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.
PULSE stabilizes mmWave human pose estimation by screening Doppler motion prompts before injecting them into spatial magnitude reasoning.
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.
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.
citing papers explorer
-
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.
-
Symmetrization of Loss Functions for Robust Training of Neural Networks in the Presence of Noisy Labels
Symmetrization of multi-class losses produces a unique convex symmetric loss that locally approximates others and supports robust neural training under label noise.
-
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.
-
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.
-
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.
-
CAST: Mitigating Object Hallucination in Large Vision-Language Models via Caption-Guided Visual Attention Steering
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.
-
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.
-
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.
-
Federated Distillation for Whole Slide Image via Gaussian-Mixture Feature Alignment and Curriculum Integration
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.
-
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.
-
ARMove: Learning to Predict Human Mobility through Agentic Reasoning
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.
-
Think before Go: Hierarchical Reasoning for Image-goal Navigation
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.
-
Position: Ideas Should be the Center of Machine Learning Research
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.
-
Fine-Grained Graph Generation through Latent Mixture Scheduling
A novel CVAE with mixture scheduling achieves fine-grained structural control in graph generation, showing high quality and controllability on five datasets.
- Trustworthy AI Suffers from Invariance Conflicts and Causality is The Solution