- Effects of Generative AI Errors on User Reliance Across Task Difficulty
Jacy Reese Anthis, Hannah Cha, Solon Barocas, Alexandra Chouldechova, Jake Hofman · Apr 5, 2026 · Citations: 0
- How Long short-term memory artificial neural network, synthetic data, and fine-tuning improve the classification of raw EEG data
Albert Nasybullin, Vladimir Maksimenko, Semen Kurkin · Apr 5, 2026 · Citations: 0
- Convolutional Neural Network and Adversarial Autoencoder in EEG images classification
Albert Nasybullin, Semen Kurkin · Apr 5, 2026 · Citations: 0
- Parent Selection Mechanisms in Elitist Crossover-Based Algorithms
Andre Opris, Denis Antipov · Apr 5, 2026 · Citations: 0
- StoryScope: Investigating idiosyncrasies in AI fiction
Jenna Russell, Rishanth Rajendhran, Mohit Iyyer, John Wieting · Apr 3, 2026 · Citations: 0
While most existing work in this space focuses on identifying surface-level signatures of AI writing, we ask instead whether AI-generated stories can be distinguished from human ones without relying on stylistic signals, focusing on…
- Self-Distilled RLVR
Chenxu Yang, Chuanyu Qin, Qingyi Si, Minghui Chen, Naibin Gu · Apr 3, 2026 · Citations: 0
Long Horizon
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- SkVM: Compiling Skills for Efficient Execution Everywhere
Le Chen, Erhu Feng, Yubin Xia, Haibo Chen · Apr 3, 2026 · Citations: 0
- JoyAI-LLM Flash: Advancing Mid-Scale LLMs with Token Efficiency
Aichen Cai, Anmeng Zhang, Anyu Li, Bo Zhang, Bohua Cai · Apr 3, 2026 · Citations: 0
Pairwise Preference
JoyAI-LLM Flash is pretrained on a massive corpus of 20 trillion tokens and further optimized through a rigorous post-training pipeline, including supervised fine-tuning (SFT), Direct Preference Optimization (DPO), and large-scale…
- ActionParty: Multi-Subject Action Binding in Generative Video Games
Alexander Pondaven, Ziyi Wu, Igor Gilitschenski, Philip Torr, Sergey Tulyakov · Apr 2, 2026 · Citations: 0
Multi Agent
However, these models are largely restricted to single-agent settings, failing to control multiple agents simultaneously in a scene.
- Steerable Visual Representations
Jona Ruthardt, Manu Gaur, Deva Ramanan, Makarand Tapaswi, Yuki M. Asano · Apr 2, 2026 · Citations: 0
- Grounded Token Initialization for New Vocabulary in LMs for Generative Recommendation
Daiwei Chen, Zhoutong Fu, Chengming Jiang, Haichao Zhang, Ran Zhou · Apr 2, 2026 · Citations: 0
Despite its simplicity, GTI outperforms both mean initialization and existing auxiliary-task adaptation methods in the majority of evaluation settings across multiple generative recommendation benchmarks, including industry-scale and public…
- Batched Contextual Reinforcement: A Task-Scaling Law for Efficient Reasoning
Bangji Yang, Hongbo Ma, Jiajun Fan, Ge Liu · Apr 2, 2026 · Citations: 0
Across both 1.5B and 4B model families, BCR reduces token usage by 15.8% to 62.6% while consistently maintaining or improving accuracy across five major mathematical benchmarks.
- No Single Best Model for Diversity: Learning a Router for Sample Diversity
Yuhan Liu, Fangyuan Xu, Vishakh Padmakumar, Daphne Ippolito, Eunsol Choi · Apr 2, 2026 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- Beyond the Assistant Turn: User Turn Generation as a Probe of Interaction Awareness in Language Models
Sarath Shekkizhar, Romain Cosentino, Adam Earle · Apr 2, 2026 · Citations: 0
- go-$m$HC: Direct Parameterization of Manifold-Constrained Hyper-Connections via Generalized Orthostochastic Matrices
Torque Dandachi, Sophia Diggs-Galligan · Apr 2, 2026 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- VOID: Video Object and Interaction Deletion
Saman Motamed, William Harvey, Benjamin Klein, Luc Van Gool, Zhuoning Yuan · Apr 2, 2026 · Citations: 0
- Omni123: Exploring 3D Native Foundation Models with Limited 3D Data by Unifying Text to 2D and 3D Generation
Chongjie Ye, Cheng Cao, Chuanyu Pan, Yiming Hao, Yihao Zhi · Apr 2, 2026 · Citations: 0
- Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing
Gengsheng Li, Tianyu Yang, Junfeng Fang, Mingyang Song, Mao Zheng · Apr 2, 2026 · Citations: 0
Long Horizon
Evaluated across five benchmarks and two model scales, SRPO achieves both the rapid early improvement of SDPO and the long-horizon stability of GRPO.
- Novel Memory Forgetting Techniques for Autonomous AI Agents: Balancing Relevance and Efficiency
Payal Fofadiya, Sunil Tiwari · Apr 2, 2026 · Citations: 0
Long Horizon
Long-horizon conversational agents require persistent memory for coherent reasoning, yet uncontrolled accumulation causes temporal decay and false memory propagation.
- The Self Driving Portfolio: Agentic Architecture for Institutional Asset Management
Andrew Ang, Nazym Azimbayev, Andrey Kim · Apr 2, 2026 · Citations: 0
Critique Edit
Agentic AI shifts the investor's role from analytical execution to oversight.
- De Jure: Iterative LLM Self-Refinement for Structured Extraction of Regulatory Rules
Keerat Guliani, Deepkamal Gill, David Landsman, Nima Eshraghi, Krishna Kumar · Apr 2, 2026 · Citations: 0
We present De Jure, a fully automated, domain-agnostic pipeline for extracting structured regulatory rules from raw documents, requiring no human annotation, domain-specific prompting, or annotated gold data.
- Crystalite: A Lightweight Transformer for Efficient Crystal Modeling
Tin Hadži Veljković, Joshua Rosenthal, Ivor Lončarić, Jan-Willem van de Meent · Apr 2, 2026 · Citations: 0
Crystalite achieves state-of-the-art results on crystal structure prediction benchmarks, and de novo generation performance, attaining the best S.U.N.
- Retrieval-Augmented Question Answering over Scientific Literature for the Electron-Ion Collider
Tina. J. Jat, T. Ghosh, Karthik Suresh · Apr 2, 2026 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- Generative AI Spotlights the Human Core of Data Science: Implications for Education
Nathan Taback · Apr 2, 2026 · Citations: 0
Generative AI (GAI) reveals an irreducible human core at the center of data science: advances in GAI should sharpen, rather than diminish, the focus on human reasoning in data science education.
- Do Emotions in Prompts Matter? Effects of Emotional Framing on Large Language Models
Minda Zhao, Yutong Yang, Chufei Peng, Rachel Gonsalves, Weiyue Li · Apr 2, 2026 · Citations: 0
Emotional tone is pervasive in human communication, yet its influence on large language model (LLM) behaviour remains unclear.
- Answering the Wrong Question: Reasoning Trace Inversion for Abstention in LLMs
Abinitha Gourabathina, Inkit Padhi, Manish Nagireddy, Subhajit Chaudhury, Prasanna Sattigeri · Apr 2, 2026 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- When to ASK: Uncertainty-Gated Language Assistance for Reinforcement Learning
Juarez Monteiro, Nathan Gavenski, Gianlucca Zuin, Adriano Veloso · Apr 2, 2026 · Citations: 0
Web Browsing
Reinforcement learning (RL) agents often struggle with out-of-distribution (OOD) scenarios, leading to high uncertainty and random behavior.
- Impact of Multimodal and Conversational AI on Learning Outcomes and Experience
Karan Taneja, Anjali Singh, Ashok K. Goel · Apr 2, 2026 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- VISTA: Visualization of Token Attribution via Efficient Analysis
Syed Ahmed, Bharathi Vokkaliga Ganesh, Jagadish Babu P, Karthick Selvaraj, Praneeth Talluri · Apr 2, 2026 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- Universal Hypernetworks for Arbitrary Models
Xuanfeng Zhou · Apr 2, 2026 · Citations: 0
Our empirical claims are threefold: (1) one fixed UHN remains competitive with direct training across vision, graph, text, and formula-regression benchmarks; (2) the same UHN supports both multi-model generalization within a family and…
- Multi-Agent Video Recommenders: Evolution, Patterns, and Open Challenges
Srivaths Ranganathan, Abhishek Dharmaratnakar, Anushree Sinha, Debanshu Das · Apr 2, 2026 · Citations: 0
Multi Agent
In response, multi-agent architectures are redefining how video recommender systems serve, learn, and adapt to both users and datasets.
- CV-18 NER: Augmented Common Voice for Named Entity Recognition from Arabic Speech
Youssef Saidi, Haroun Elleuch, Fethi Bougares · Apr 2, 2026 · Citations: 0
We benchmark both pipeline systems (ASR + text NER) and E2E models based on Whisper and AraBEST-RQ.
- Blinded Radiologist and LLM-Based Evaluation of LLM-Generated Japanese Translations of Chest CT Reports: Comparative Study
Yosuke Yamagishi, Atsushi Takamatsu, Yasunori Hamaguchi, Tomohiro Kikuchi, Shouhei Hanaoka · Apr 2, 2026 · Citations: 0
Pairwise Preference
A board-certified radiologist and a radiology resident independently performed blinded pairwise evaluations across 4 criteria: terminology accuracy, readability, overall quality, and radiologist-style authenticity.
- LEO: Graph Attention Network based Hybrid Multi Sensor Extended Object Fusion and Tracking for Autonomous Driving Applications
Mayank Mayank, Bharanidhar Duraisamy, Florian Geiss · Apr 2, 2026 · Citations: 0
Long Horizon
Evaluations on the Mercedes-Benz DRIVE PILOT SAE L3 dataset demonstrate real-time computational efficiency suitable for production systems; additional validation on public datasets such as View of Delft (VoD) further confirms cross-dataset…
- Towards Position-Robust Talent Recommendation via Large Language Models
Silin Du, Hongyan Liu · Apr 2, 2026 · Citations: 0
We design evaluation methods to detect position bias and token bias and training-free debiasing methods.
- From High-Dimensional Spaces to Verifiable ODD Coverage for Safety-Critical AI-based Systems
Thomas Stefani, Johann Maximilian Christensen, Elena Hoemann, Frank Köster, Sven Hallerbach · Apr 2, 2026 · Citations: 0
Long Horizon
While Artificial Intelligence (AI) offers transformative potential for operational performance, its deployment in safety-critical domains such as aviation requires strict adherence to rigorous certification standards.
- Neuro-RIT: Neuron-Guided Instruction Tuning for Robust Retrieval-Augmented Language Model
Jaemin Kim, Jae O Lee, Sumyeong Ahn, Seo Yeon Park · Apr 2, 2026 · Citations: 0
Extensive experiments across diverse QA benchmarks demonstrate that Neuro-RIT consistently outperforms strong baselines and robustness-enhancing methods.
- TRU: Targeted Reverse Update for Efficient Multimodal Recommendation Unlearning
Zhanting Zhou, KaHou Tam, Ziqiang Zheng, Zeyu Ma, Zhanting Zhou · Apr 2, 2026 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- The Expert Strikes Back: Interpreting Mixture-of-Experts Language Models at Expert Level
Jeremy Herbst, Jae Hee Lee, Stefan Wermter · Apr 2, 2026 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- Adam's Law: Textual Frequency Law on Large Language Models
Hongyuan Adam Lu, Z. L., Victor Wei, Zefan Zhang, Zhao Hong · Apr 2, 2026 · Citations: 0
While textual frequency has been validated as relevant to human cognition in reading speed, its relatedness to Large Language Models (LLMs) is seldom studied.
- Quantifying Self-Preservation Bias in Large Language Models
Matteo Migliarini, Joaquin Pereira Pizzini, Luca Moresca, Valerio Santini, Indro Spinelli · Apr 2, 2026 · Citations: 0
Instrumental convergence predicts that sufficiently advanced AI agents will resist shutdown, yet current safety training (RLHF) may obscure this risk by teaching models to deny self-preservation motives.
- Do Lexical and Contextual Coreference Resolution Systems Degrade Differently under Mention Noise? An Empirical Study on Scientific Software Mentions
Atilla Kaan Alkan, Felix Grezes, Jennifer Lynn Bartlett, Anna Kelbert, Kelly Lockhart · Apr 2, 2026 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- AstroConcepts: A Large-Scale Multi-Label Classification Corpus for Astrophysics
Atilla Kaan Alkan, Felix Grezes, Sergi Blanco-Cuaresma, Jennifer Lynn Bartlett, Daniel Chivvis · Apr 2, 2026 · Citations: 0
Our evaluation reveals three key patterns that provide new insights into scientific text classification.
- Brief Is Better: Non-Monotonic Chain-of-Thought Budget Effects in Function-Calling Language Agents
Xuan Qi · Apr 2, 2026 · Citations: 0
Tool Use
Chain-of-thought (CoT) reasoning is widely assumed to improve agent performance, but the relationship between reasoning length and accuracy in structured tool-use settings remains poorly understood.
- TRACE-Bot: Detecting Emerging LLM-Driven Social Bots via Implicit Semantic Representations and AIGC-Enhanced Behavioral Patterns
Zhongbo Wang, Zhiyu Lin, Zhu Wang, Haizhou Wang · Apr 2, 2026 · Citations: 0
Large Language Model-driven (LLM-driven) social bots pose a growing threat to online discourse by generating human-like content that evades conventional detection.
- MTI: A Behavior-Based Temperament Profiling System for AI Agents
Jihoon Jeong · Apr 2, 2026 · Citations: 0
Existing approaches either borrow human personality dimensions and rely on self-report (which diverges from actual behavior in LLMs) or treat behavioral variation as a defect rather than a trait.
- GaelEval: Benchmarking LLM Performance for Scottish Gaelic
Peter Devine, William Lamb, Beatrice Alex, Ignatius Ezeani, Dawn Knight · Apr 2, 2026 · Citations: 0
We introduce GaelEval, the first multi-dimensional benchmark for Gaelic, comprising: (i) an expert-authored morphosyntactic MCQA task; (ii) a culturally grounded translation benchmark and (iii) a large-scale cultural knowledge Q&A task.
- Intelligent Cloud Orchestration: A Hybrid Predictive and Heuristic Framework for Cost Optimization
Heet Nagoriya, Komal Rohit · Apr 2, 2026 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- SEAL: An Open, Auditable, and Fair Data Generation Framework for AI-Native 6G Networks
Sunder Ali Khowaja, Kapal Dev, Engin Zeydan, Madhusanka Liyanage · Apr 2, 2026 · Citations: 0
In this regard, we propose the Synthetic Data Generation with Ethics Audit Loop (SEAL) framework, which extends baseline modular pipelines with an Ethical and Regulatory Compliance by Design (ERCD) module and a Federated Learning (FL)…
- LLM-as-a-Judge for Time Series Explanations
Preetham Sivalingam, Murari Mandal, Saurabh Deshpande, Dhruv Kumar · Apr 2, 2026 · Citations: 0
Although modern models generate textual interpretations of numerical signals, existing evaluation methods are limited: reference based similarity metrics and consistency checking models require ground truth explanations, while traditional…
- Reliable Control-Point Selection for Steering Reasoning in Large Language Models
Haomin Zhuang, Hojun Yoo, Xiaonan Luo, Kehan Guo, Xiangliang Zhang · Apr 2, 2026 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- CASHG: Context-Aware Stylized Online Handwriting Generation
Jinsu Shin, Sungeun Hong, JinYeong Bak · Apr 2, 2026 · Citations: 0
- Prosodic ABX: A Language-Agnostic Method for Measuring Prosodic Contrast in Speech Representations
Haitong Sun, Stephen McIntosh, Kwanghee Choi, Eunjung Yeo, Daisuke Saito · Apr 2, 2026 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- Optimizing RAG Rerankers with LLM Feedback via Reinforcement Learning
Yuhang Wu, Xiangqing Shen, Fanfan Wang, Cangqi Zhou, Zhen Wu · Apr 2, 2026 · Citations: 0
Pairwise Preference
However, current reranking models are typically optimized on static human annotated relevance labels in isolation, decoupled from the downstream generation process.
- Mining Instance-Centric Vision-Language Contexts for Human-Object Interaction Detection
Soo Won Seo, KyungChae Lee, Hyungchan Cho, Taein Son, Nam Ik Cho · Apr 2, 2026 · Citations: 0
Human-Object Interaction (HOI) detection aims to localize human-object pairs and classify their interactions from a single image, a task that demands strong visual understanding and nuanced contextual reasoning.
- Diff-KD: Diffusion-based Knowledge Distillation for Collaborative Perception under Corruptions
Pengcheng Lyu, Chaokun Zhang, Gong Chen, Tao Tang, Zhaoxiang Luo · Apr 2, 2026 · Citations: 0
Multi Agent
Multi-agent collaborative perception enables autonomous systems to overcome individual sensing limits through collective intelligence.
- Ouroboros: Dynamic Weight Generation for Recursive Transformers via Input-Conditioned LoRA Modulation
Jaber Jaber, Osama Jaber · Apr 2, 2026 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- Goose: Anisotropic Speculation Trees for Training-Free Speculative Decoding
Tao Jin, Phuong Minh Nguyen, Naoya Inoue · Apr 2, 2026 · Citations: 0
We observe that two common training-free token sources - n-gram matches copied from the input context, and statistical predictions from prior forward passes - differ dramatically in acceptance rate (~6x median gap, range 2-18x across five…
- BidirLM: From Text to Omnimodal Bidirectional Encoders by Adapting and Composing Causal LLMs
Nicolas Boizard, Théo Deschamps-Berger, Hippolyte Gisserot-Boukhlef, Céline Hudelot, Pierre Colombo · Apr 2, 2026 · Citations: 0
This open-source recipe, designed for any causal decoder LLM, yields BidirLM, a family of five encoders that outperform alternatives on text, vision, and audio representation benchmarks.
- Tracking the emergence of linguistic structure in self-supervised models learning from speech
Marianne de Heer Kloots, Martijn Bentum, Hosein Mohebbi, Charlotte Pouw, Gaofei Shen · Apr 2, 2026 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.