LLM - 2026-04
LLM - 2026-04
| Publish Date | Title | Authors | Translate | Read | Code | |
|---|---|---|---|---|---|---|
| 2026-04-01 | HippoCamp: Benchmarking Contextual Agents on Personal Computers | Zhe Yang et.al. | 2604.01221 | translate | read | null |
| 2026-04-01 | Universal YOCO for Efficient Depth Scaling | Yutao Sun et.al. | 2604.01220 | translate | read | null |
| 2026-04-01 | LLM REgression with a Latent Iterative State Head | Yiheng Su et.al. | 2604.01206 | translate | read | null |
| 2026-04-01 | AgentWatcher: A Rule-based Prompt Injection Monitor | Yanting Wang et.al. | 2604.01194 | translate | read | null |
| 2026-04-01 | Embarrassingly Simple Self-Distillation Improves Code Generation | Ruixiang Zhang et.al. | 2604.01193 | translate | read | null |
| 2026-04-01 | True (VIS) Lies: Analyzing How Generative AI Recognizes Intentionality, Rhetoric, and Misleadingness in Visualization Lies | Graziano Blasilli et.al. | 2604.01181 | translate | read | null |
| 2026-04-01 | Online Reasoning Calibration: Test-Time Training Enables Generalizable Conformal LLM Reasoning | Cai Zhou et.al. | 2604.01170 | translate | read | null |
| 2026-04-01 | Reasoning Shift: How Context Silently Shortens LLM Reasoning | Gleb Rodionov et.al. | 2604.01161 | translate | read | null |
| 2026-04-01 | Brainstacks: Cross-Domain Cognitive Capabilities via Frozen MoE-LoRA Stacks for Continual LLM Learning | Mohammad R. Abu Ayyash et.al. | 2604.01152 | translate | read | null |
| 2026-04-01 | SERSEM: Selective Entropy-Weighted Scoring for Membership Inference in Code Language Models | Kıvanç Kuzey Dikici et.al. | 2604.01147 | translate | read | null |
| 2026-04-01 | Multi-Agent LLM Governance for Safe Two-Timescale Reinforcement Learning in SDN-IoT Defense | Saeid Jamshidi et.al. | 2604.01127 | translate | read | null |
| 2026-04-01 | CARE: Privacy-Compliant Agentic Reasoning with Evidence Discordance | Haochen Liu et.al. | 2604.01113 | translate | read | null |
| 2026-04-01 | Adversarial Moral Stress Testing of Large Language Models | Saeid Jamshidi et.al. | 2604.01108 | translate | read | null |
| 2026-04-01 | Temporal Dependencies in In-Context Learning: The Role of Induction Heads | Anooshka Bajaj et.al. | 2604.01094 | translate | read | null |
| 2026-04-01 | Asymptotically Optimal Sequential Testing with Heterogeneous LLMs | Guokai Li et.al. | 2604.01086 | translate | read | null |
| 2026-04-01 | Automated Framework to Evaluate and Harden LLM System Instructions against Encoding Attacks | Anubhab Sahu et.al. | 2604.01039 | translate | read | null |
| 2026-04-01 | Fast and Accurate Probing of In-Training LLMs’ Downstream Performances | Zhichen Liu et.al. | 2604.01025 | translate | read | null |
| 2026-04-01 | OrgAgent: Organize Your Multi-Agent System like a Company | Yiru Wang et.al. | 2604.01020 | translate | read | null |
| 2026-04-01 | PDA: Text-Augmented Defense Framework for Robust Vision-Language Models against Adversarial Image Attacks | Jingning Xu et.al. | 2604.01010 | translate | read | null |
| 2026-04-01 | Query-Conditioned Evidential Keyframe Sampling for MLLM-Based Long-Form Video Understanding | Yiheng Wang et.al. | 2604.01002 | translate | read | null |
| 2026-04-01 | Uncertainty-Aware Variational Reward Factorization via Probabilistic Preference Bases for LLM Personalization | Gyuseok Lee et.al. | 2604.00997 | translate | read | null |
| 2026-04-01 | Multimodal Analysis of State-Funded News Coverage of the Israel-Hamas War on YouTube Shorts | Daniel Miehling et.al. | 2604.00994 | translate | read | null |
| 2026-04-01 | VisG AV-HuBERT: Viseme-Guided AV-HuBERT | Aristeidis Papadopoulos et.al. | 2604.00982 | translate | read | null |
| 2026-04-01 | FlexAI: A Multi-modal Solution for Delivering Personalized and Adaptive Fitness Interventions | Shivangi Agarwal et.al. | 2604.00968 | translate | read | null |
| 2026-04-01 | Auditing the Reliability of Multimodal Generative Search | Erfan Samieyan Sahneh et.al. | 2604.00944 | translate | read | null |
| 2026-04-01 | Positional Cognitive Specialization: Where Do LLMs Learn To Comprehend and Speak Your Language? | Luis Frentzen Salim et.al. | 2604.00923 | translate | read | null |
| 2026-04-01 | Investigating Autonomous Agent Contributions in the Wild: Activity Patterns and Code Change over Time | Razvan Mihai Popescu et.al. | 2604.00917 | translate | read | null |
| 2026-04-01 | Beyond Symbolic Solving: Multi Chain-of-Thought Voting for Geometric Reasoning in Large Language Models | Md. Abu Bakor Siddique et.al. | 2604.00890 | translate | read | null |
| 2026-04-01 | A 4D Representation for Training-Free Agentic Reasoning from Monocular Laparoscopic Video | Maximilian Fehrentz et.al. | 2604.00867 | translate | read | null |
| 2026-04-01 | Policy Improvement Reinforcement Learning | Huaiyang Wang et.al. | 2604.00860 | translate | read | null |
| 2026-04-01 | Reliability of Large Language Models for Design Synthesis: An Empirical Study of Variance, Prompt Sensitivity, and Method Scaffolding | Rabia Iftikhar et.al. | 2604.00851 | translate | read | null |
| 2026-04-01 | Agentic Tool Use in Large Language Models | Jinchao Hu et.al. | 2604.00835 | translate | read | null |
| 2026-04-01 | Optimal Brain Decomposition for Accurate LLM Low-Rank Approximation | Yuhang Li et.al. | 2604.00821 | translate | read | null |
| 2026-04-01 | Emotion Entanglement and Bayesian Inference for Multi-Dimensional Emotion Understanding | Hemanth Kotaprolu et.al. | 2604.00819 | translate | read | null |
| 2026-04-01 | Misconception Acquisition Dynamics in Large Language Models | Naiming Liu et.al. | 2604.00818 | translate | read | null |
| 2026-04-01 | A novel three-step approach to forecast firm-specific technology convergence opportunity via multi-dimensional feature fusion | Fu Gu et.al. | 2604.00803 | translate | read | null |
| 2026-04-01 | Multimodal Language Models Cannot Spot Spatial Inconsistencies | Om Khangaonkar et.al. | 2604.00799 | translate | read | null |
| 2026-04-01 | RefineRL: Advancing Competitive Programming with Self-Refinement Reinforcement Learning | Shaopeng Fu et.al. | 2604.00790 | translate | read | null |
| 2026-04-01 | Scalable Pretraining of Large Mixture of Experts Language Models on Aurora Super Computer | Dharma Teja Vooturi et.al. | 2604.00785 | translate | read | null |
| 2026-04-01 | An Approach to Enriching Surgical Video Datasets for Fine-Grained Spatial-Temporal Understanding of Vision-Language Models | Lennart Maack et.al. | 2604.00784 | translate | read | null |
| 2026-04-01 | From Early Encoding to Late Suppression: Interpreting LLMs on Character Counting Tasks | Ayan Datta et.al. | 2604.00778 | translate | read | null |
| 2026-04-01 | Translating With Feeling: Centering Translator Perspectives within Translation Technologies | Daniel Chechelnitsky et.al. | 2604.00758 | translate | read | null |
| 2026-04-01 | Spectral Compact Training: Pre-Training Large Language Models via Permanent Truncated SVD and Stiefel QR Retraction | Björn Roman Kohlberger et.al. | 2604.00733 | translate | read | null |
| 2026-04-01 | Exploring Silent Data Corruption as a Reliability Challenge in LLM Training | Anton Altenbernd et.al. | 2604.00726 | translate | read | null |
| 2026-04-01 | LangMARL: Natural Language Multi-Agent Reinforcement Learning | Huaiyuan Yao et.al. | 2604.00722 | translate | read | null |
| 2026-04-01 | SCPatcher: Automated Smart Contract Code Repair via Retrieval-Augmented Generation and Knowledge Graph | Xiaoqi Li et.al. | 2604.00687 | translate | read | null |
| 2026-04-01 | CL-VISTA: Benchmarking Continual Learning in Video Large Language Models | Haiyang Guo et.al. | 2604.00677 | translate | read | null |
| 2026-04-01 | Streaming Model Cascades for Semantic SQL | Paweł Liskowski et.al. | 2604.00660 | translate | read | null |
| 2026-04-01 | LibScan: Smart Contract Library Misuse Detection with Iterative Feedback and Static Verification | Yishun Wang et.al. | 2604.00657 | translate | read | null |
| 2026-04-01 | StretchBot: A Neuro-Symbolic Framework for Adaptive Guidance with Assistive Robots | Luca Vogelgesang et.al. | 2604.00628 | translate | read | null |
| 2026-04-01 | A Survey of On-Policy Distillation for Large Language Models | Mingyang Song et.al. | 2604.00626 | translate | read | null |
| 2026-04-01 | English to Central Kurdish Speech Translation: Corpus Creation, Evaluation, and Orthographic Standardization | Mohammad Mohammadamini et.al. | 2604.00613 | translate | read | null |
| 2026-04-01 | Speech LLMs are Contextual Reasoning Transcribers | Keqi Deng et.al. | 2604.00610 | translate | read | null |
| 2026-04-01 | KG-CMI: Knowledge graph enhanced cross-Mamba interaction for medical visual question answering | Xianyao Zheng et.al. | 2604.00601 | translate | read | null |
| 2026-04-01 | More Human, More Efficient: Aligning Annotations with Quantized SLMs | Jiayu Wang et.al. | 2604.00586 | translate | read | null |
| 2026-04-01 | A Japanese Benchmark for Evaluating Social Bias in Reasoning Based on Attribution Theory | Taihei Shiotani et.al. | 2604.00568 | translate | read | null |
| 2026-04-01 | STAR: Mitigating Cascading Errors in Spatial Reasoning via Turn-point Alignment and Segment-level DPO | Pukun Zhao et.al. | 2604.00558 | translate | read | null |
| 2026-04-01 | Ontology-Constrained Neural Reasoning in Enterprise Agentic Systems: A Neurosymbolic Architecture for Domain-Grounded AI Agents | Thanh Luong Tuan et.al. | 2604.00555 | translate | read | null |
| 2026-04-01 | LLM-supported document separation for printed reviews from zbMATH Open | Ivan Pluzhnikov et.al. | 2604.00554 | translate | read | null |
| 2026-04-01 | BloClaw: An Omniscient, Multi-Modal Agentic Workspace for Next-Generation Scientific Discovery | Yao Qin et.al. | 2604.00550 | translate | read | null |
| 2026-04-01 | Optimsyn: Influence-Guided Rubrics Optimization for Synthetic Data Generation | Zhiting Fan et.al. | 2604.00536 | translate | read | null |
| 2026-04-01 | Learning from Many and Adapting to the Unknown in Open-set Test Streams | Xiao Zhang et.al. | 2604.00533 | translate | read | null |
| 2026-04-01 | Do Agents Repair When Challenged – or Just Reply? Challenge, Repair, and Public Correction in a Deployed Agent Forum | Luyang Zhang et.al. | 2604.00518 | translate | read | null |
| 2026-04-01 | MOON3.0: Reasoning-aware Multimodal Representation Learning for E-commerce Product Understanding | Junxian Wu et.al. | 2604.00513 | translate | read | null |
| 2026-04-01 | Adaptive Parallel Monte Carlo Tree Search for Efficient Test-time Compute Scaling | Hongbeen Kim et.al. | 2604.00510 | translate | read | null |
| 2026-04-01 | A Reasoning-Enabled Vision-Language Foundation Model for Chest X-ray Interpretation | Yabin Zhang et.al. | 2604.00493 | translate | read | null |
| 2026-04-01 | Adapting Text LLMs to Speech via Multimodal Depth Up-Scaling | Kazuki Yano et.al. | 2604.00489 | translate | read | null |
| 2026-04-01 | Competition and Cooperation of LLM Agents in Games | Jiayi Yao et.al. | 2604.00487 | translate | read | null |
| 2026-04-01 | The Silicon Mirror: Dynamic Behavioral Gating for Anti-Sycophancy in LLM Agents | Harshee Jignesh Shah et.al. | 2604.00478 | translate | read | null |
| 2026-04-01 | Logarithmic Scores, Power-Law Discoveries: Disentangling Measurement from Coverage in Agent-Based Evaluation | HyunJoon Jung et.al. | 2604.00477 | translate | read | null |
| 2026-04-01 | LDMDroid: Leveraging LLMs for Detecting Data Manipulation Errors in Android Apps | Xiangyang Xiao et.al. | 2604.00458 | translate | read | null |
| 2026-04-01 | Towards Reliable Truth-Aligned Uncertainty Estimation in Large Language Models | Ponhvoan Srey et.al. | 2604.00445 | translate | read | null |
| 2026-04-01 | TR-ICRL: Test-Time Rethinking for In-Context Reinforcement Learning | Wenxuan Jiang et.al. | 2604.00438 | translate | read | null |
| 2026-04-01 | Secure Forgetting: A Framework for Privacy-Driven Unlearning in Large Language Model (LLM)-Based Agents | Dayong Ye et.al. | 2604.00430 | translate | read | null |
| 2026-04-01 | G-Drift MIA: Membership Inference via Gradient-Induced Feature Drift in LLMs | Ravi Ranjan et.al. | 2604.00419 | translate | read | null |
| 2026-04-01 | The 1st Winner for 5th PVUW MeViS-Text Challenge: Strong MLLMs Meet SAM3 for Referring Video Object Segmentation | Xusheng He et.al. | 2604.00404 | translate | read | null |
| 2026-04-01 | Advancing Complex Video Object Segmentation via Tracking-Enhanced Prompt: The 1st Winner for 5th PVUW MOSE Challenge | Jinrong Zhang et.al. | 2604.00395 | translate | read | null |
| 2026-04-01 | Locally Confident, Globally Stuck: The Quality-Exploration Dilemma in Diffusion Language Models | Liancheng Fang et.al. | 2604.00375 | translate | read | null |
| 2026-04-01 | Signals: Trajectory Sampling and Triage for Agentic Interactions | Shuguang Chen et.al. | 2604.00356 | translate | read | null |
| 2026-04-01 | Agent Q-Mix: Selecting the Right Action for LLM Multi-Agent Systems through Reinforcement Learning | Eric Hanchen Jiang et.al. | 2604.00344 | translate | read | null |
| 2026-04-01 | Is One Token All It Takes? Graph Pooling Tokens for LLM-based GraphQA | Ankit Grover et.al. | 2604.00342 | translate | read | null |
(<a href=../LLM.md>back to LLM</a>)