| When Persuasion Overrides Truth in Multi-Agent LLM Debates: Introducing a Confidence-Weighted Persuasion Override Rate (CW-POR) | Apr 1, 2025 | Language ModelingLanguage Modelling | —Unverified | 0 |
| Unleashing the Power of Pre-trained Encoders for Universal Adversarial Attack Detection | Apr 1, 2025 | Adversarial AttackAdversarial Attack Detection | —Unverified | 0 |
| VerifiAgent: a Unified Verification Agent in Language Model Reasoning | Apr 1, 2025 | Language ModelingLanguage Modelling | CodeCode Available | 0 |
| Multi-Token Attention | Apr 1, 2025 | Language ModelingLanguage Modelling | —Unverified | 0 |
| Command A: An Enterprise-Ready Large Language Model | Apr 1, 2025 | Language ModelingLanguage Modelling | —Unverified | 0 |
| Detecting PTSD in Clinical Interviews: A Comparative Analysis of NLP Methods and Large Language Models | Apr 1, 2025 | Language ModelingLanguage Modelling | —Unverified | 0 |
| Automated detection of atomicity violations in large-scale systems | Apr 1, 2025 | Language ModelingLanguage Modelling | —Unverified | 0 |
| ShieldGemma 2: Robust and Tractable Image Content Moderation | Apr 1, 2025 | Image GenerationLanguage Modeling | —Unverified | 0 |
| 4th PVUW MeViS 3rd Place Report: Sa2VA | Apr 1, 2025 | Language ModelingLanguage Modelling | CodeCode Available | 5 |
| CrowdVLM-R1: Expanding R1 Ability to Vision Language Model for Crowd Counting using Fuzzy Group Relative Policy Reward | Mar 31, 2025 | Crowd CountingLanguage Modeling | CodeCode Available | 1 |
