Instant research discovery

Search and browse ingested papers with intelligence signals and fast filtering.

Showing 421-450 of 6456 papers (page 15 of 216)

PaperIntel
TREX: Trajectory Explanations for Multi-Objective Reinforcement Learning

Juan C. Rosero, Ivana Dusparic, Dilina Rajapakse

Published: 2026-03-23Area: cs.LGCitations: -

Tags: ai-safety, cslg, preprint

E5 / R3 (95%)
Tacit Knowledge Management with Generative AI: Proposal of the GenAI SECI Model

Naoshi Uchihira

Published: 2026-03-23Area: cs.AICitations: -

Tags: ai-safety, csai, preprint

E5 / R3 (97%)
The Presupposition Problem in Representation Genesis

Yiling Wu

Published: 2026-03-23Area: cs.AICitations: -

Tags: ai-safety, csai, preprint

E8 / R4 (95%)
The Reasoning Error About Reasoning: Why Different Types of Reasoning Require Different Representational Structures

Yiling Wu

Published: 2026-03-23Area: cs.AICitations: -

Tags: ai-safety, csai, preprint

E6 / R3 (96%)
ThinkJEPA: Empowering Latent World Models with Large Vision-Language Reasoning Model

Ang Li, Shwai He, Yijiang Li, Tushar Nagarajan

Published: 2026-03-23Area: cs.CVCitations: -

Tags: ai-safety, cscv, preprint

E4 / R3 (95%)
Thinking Deeper, Not Longer: Depth-Recurrent Transformers for Compositional Generalization

Hung-Hsuan Chen

Published: 2026-03-23Area: cs.LGCitations: -

Tags: ai-safety, cslg, preprint

E5 / R4 (96%)
Three Creates All: You Only Sample 3 Steps

Yuren Cai, Zhihui Liu, Songzhi Su, Zongqing Li

Published: 2026-03-23Area: cs.LGCitations: -

Tags: ai-safety, cslg, preprint

E5 / R3 (94%)
TiCo: Time-Controllable Training for Spoken Dialogue Models

En-Pei Hu, Hung-yi Lee, Wei-Chih Chen, Kai-Wei Chang

Published: 2026-03-23Area: cs.CLCitations: -

Tags: cscl, ai-safety, preprint

E5 / R3 (95%)
Tiny Inference-Time Scaling with Latent Verifiers

Lorenzo Baraldi, Evelyn Turri, Marcella Cornia, Rita Cucchiara

Published: 2026-03-23Area: cs.CVCitations: -

Tags: ai-safety, cscv, preprint

E5 / R3 (95%)
To Agree or To Be Right? The Grounding-Sycophancy Tradeoff in Medical Vision-Language Models

Kevin Desai, OFM Riaz Rahman Aranya

Published: 2026-03-23Area: cs.CVCitations: -

Tags: ai-safety, cscv, preprint

E9 / R3 (99%)
Toward Faithful Segmentation Attribution via Benchmarking and Dual-Evidence Fusion

Kevin Desai, OFM Riaz Rahman Aranya, Zijie Zhang, Abu Noman Md Sakib

Published: 2026-03-23Area: cs.CVCitations: -

Tags: ai-safety, cscv, preprint

E5 / R3 (95%)
Toward a Theory of Hierarchical Memory for Language Agents

Ali Parsaee, Osmar Zaiane, Yashar Talebirad, Csongor Y. Szepesvari

Published: 2026-03-23Area: cs.IRCitations: 25

Tags: ai-safety, csir, preprint

E7 / R3 (93%)
Towards Secure Retrieval-Augmented Generation: A Comprehensive Review of Threats, Defenses and Benchmarks

Qiao Yuan, Mei Wang, Pengcheng Liu, Hongwei Zhou

Published: 2026-03-23Area: cs.CRCitations: -

Tags: ai-safety, cscr, preprint

E7 / R4 (98%)
TrustTrade: Human-Inspired Selective Consensus Reduces Decision Uncertainty in LLM Trading Agents

Sunghoon Yoon, Minghan Li, Weiyue Li, Mengyu Wang

Published: 2026-03-23Area: cs.CECitations: -

Tags: csce, ai-safety, preprint

E4 / R3 (95%)
Uncertainty-guided Compositional Alignment with Part-to-Whole Semantic Representativeness in Hyperbolic Vision-Language Models

Se Young Chun, Hayeon Kim, Ji Ha Jang, Junghun James Kim

Published: 2026-03-23Area: cs.CVCitations: -

Tags: alignment-training, ai-safety, cscv, preprint

E6 / R3 (94%)
Uncertainty-guided Compositional Alignment with Part-to-Whole Semantic Representativeness in Hyperbolic Vision-Language Models

Se Young Chun, Hayeon Kim, Ji Ha Jang, Junghun James Kim

Published: 2026-03-23Area: cs.CVCitations: -

Tags: alignment-training, ai-safety, cscv, preprint

E6 / R3 (94%)
Understanding LLM Performance Degradation in Multi-Instance Processing: The Roles of Instance Count and Context Length

Jose Camacho-Collados, Mohammad Taher Pilehvar, Jingxuan Chen

Published: 2026-03-23Area: cs.AICitations: -

Tags: ai-safety, csai, preprint

E5 / R2 (95%)
UniMotion: A Unified Framework for Motion-Text-Vision Understanding and Generation

Shuang Chen, Ziyi Wang, Mengyuan Liu, Xinshun Wang

Published: 2026-03-23Area: cs.CVCitations: -

Tags: ai-safety, cscv, preprint

E5 / R3 (94%)
Unified-MAS: Universally Generating Domain-Specific Nodes for Empowering Automatic Multi-Agent Systems

Zixuan Wang, Weiquan Huang, Minzhi Li, Sudong Wang

Published: 2026-03-23Area: cs.AICitations: -

Tags: ai-safety, csai, preprint

E5 / R3 (96%)
Unveiling the Mechanism of Continuous Representation Full-Waveform Inversion: A Wave Based Neural Tangent Kernel Framework

Deyu Meng, Ruihua Chen, Yisi Luo, Bangyu Wu

Published: 2026-03-23Area: cs.LGCitations: -

Tags: ai-safety, cslg, preprint

E5 / R3 (95%)
Upper Entropy for 2-Monotone Lower Probabilities

Sébastien Destercke, Tuan-Anh Vu, Frédéric Pichon

Published: 2026-03-23Area: cs.LGCitations: -

Tags: ai-safety, cslg, preprint

E6 / R3 (93%)
Wake Up to the Past: Using Memory to Model Fluid Wake Effects on Robots

Luca Vendruscolo, Amanda Prorok, Ajay Shankar, Eduardo Sebastián

Published: 2026-03-23Area: cs.ROCitations: -

Tags: ai-safety, csro, preprint

E6 / R3 (95%)
What Do World Models Learn in RL? Probing Latent Representations in Learned Environment Simulators

Xinyu Zhang

Published: 2026-03-23Area: cs.LGCitations: -

Tags: ai-safety, cslg, preprint

E5 / R3 (95%)
When Documents Disagree: Measuring Institutional Variation in Transplant Guidance with Retrieval-Augmented Language Models

Rema Padman, Yubo Li, Ramayya Krishnan

Published: 2026-03-23Area: cs.IRCitations: -

Tags: ai-safety, csir, preprint

E4 / R3 (94%)
When Exploration Comes for Free with Mixture-Greedy: Do we need UCB in Diversity-Aware Multi-Armed Bandits?

Farzan Farnia, Bahar Dibaei Nia

Published: 2026-03-23Area: cs.LGCitations: -

Tags: ai-safety, cslg, preprint

E5 / R2 (93%)
When Visuals Aren't the Problem: Evaluating Vision-Language Models on Misleading Data Visualizations

Grace Guo, Raj Sanjay Shah, Harsh Nishant Lalai, Hanspeter Pfister

Published: 2026-03-23Area: cs.CVCitations: -

Tags: ai-safety, cscv, preprint

E5 / R2 (94%)
WorldCache: Content-Aware Caching for Accelerated Video World Models

Umair Nawaz, Ahmed Heakl, Salman Khan, Ufaq Khan

Published: 2026-03-23Area: cs.CVCitations: -

Tags: ai-safety, cscv, preprint

E6 / R3 (97%)
flexvec: SQL Vector Retrieval with Programmatic Embedding Modulation

Damian Delmas

Published: 2026-03-23Area: cs.IRCitations: -

Tags: ai-safety, csir, preprint

E5 / R3 (97%)
mSFT: Addressing Dataset Mixtures Overfiting Heterogeneously in Multi-task SFT

Jeyoung Jeon, Soowon Oh, Yujin Cheon, Youngjin Song

Published: 2026-03-23Area: cs.LGCitations: -

Tags: ai-safety, cslg, preprint

E7 / R3 (94%)
mSFT: Addressing Dataset Mixtures Overfitting Heterogeneously in Multi-task SFT

Jeyoung Jeon, Soowon Oh, Yujin Cheon, Youngjin Song

Published: 2026-03-23Area: cs.LGCitations: -

Tags: ai-safety, cslg, preprint

E7 / R3 (93%)