- GR-SAP: Generative Replay for Safety Alignment Preservation during Fine-Tuning
Zhouxiang Fang, Jiawei Zhou, Hanjie Chen · Mar 10, 2026 · Citations: 0
Recent studies show that the safety alignment of large language models (LLMs) can be easily compromised even by seemingly non-adversarial fine-tuning.
- S-GRADES -- Studying Generalization of Student Response Assessments in Diverse Evaluative Settings
Tasfia Seuti, Sagnik Ray Choudhury · Mar 10, 2026 · Citations: 0
We introduce S-GRADES (Studying Generalization of Student Response Assessments in Diverse Evaluative Settings), a web-based benchmark that consolidates 14 diverse grading datasets under a unified interface with standardized access and…
- Sabiá-4 Technical Report
Thiago Laitz, Thales Sales Almeida, Hugo Abonizio, Roseval Malaquias Junior, Giovana Kerche Bonás · Mar 10, 2026 · Citations: 0
Pairwise Preference Tool Use
The models were developed through a four-stage training pipeline: continued pre-training on Portuguese and Brazilian legal corpora, long-context extension to 128K tokens, supervised fine-tuning on instruction data spanning chat, code, legal…
- ViDia2Std: A Parallel Corpus and Methods for Low-Resource Vietnamese Dialect-to-Standard Translation
Khoa Anh Ta, Nguyen Van Dinh, Kiet Van Nguyen · Mar 10, 2026 · Citations: 0
To assess annotation consistency, we define a semantic mapping agreement metric that accounts for synonymous standard mappings across annotators.
- Adaptive Activation Cancellation for Hallucination Mitigation in Large Language Models
Eric Yocam, Varghese Vaidyan, Gurcan Comert, Paris Kalathas, Yong Wang · Mar 10, 2026 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- Video-Based Reward Modeling for Computer-Use Agents
Linxin Song, Jieyu Zhang, Huanxin Sheng, Taiwei Shi, Gupta Rahul · Mar 10, 2026 · Citations: 0
Long Horizon
Computer-using agents (CUAs) are becoming increasingly capable; however, it remains difficult to scale evaluation of whether a trajectory truly fulfills a user instruction.
- Calibration-Reasoning Framework for Descriptive Speech Quality Assessment
Elizaveta Kostenok, Mathieu Salzmann, Milos Cernak · Mar 10, 2026 · Citations: 0
With this approach we reach state-of-the-art results of 0.71 mean PCC score on the multidimensional QualiSpeech benchmark and 13% improvement in MOS prediction driven by RL-based reasoning.
- OpenClaw-RL: Train Any Agent Simply by Talking
Yinjie Wang, Xuyang Chen, Xiaolong Jin, Mengdi Wang, Ling Yang · Mar 10, 2026 · Citations: 0
Every agent interaction generates a next-state signal, namely the user reply, tool output, terminal or GUI state change that follows each action, yet no existing agentic RL system recovers it as a live, online learning source.
- ReMix: Reinforcement routing for mixtures of LoRAs in LLM finetuning
Ruizhong Qiu, Hanqing Zeng, Yinglong Xia, Yiwen Meng, Ren Chen · Mar 10, 2026 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- Lost in Backpropagation: The LM Head is a Gradient Bottleneck
Nathan Godey, Yoav Artzi · Mar 10, 2026 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- Reason and Verify: A Framework for Faithful Retrieval-Augmented Generation
Eeham Khan, Luis Rodriguez, Marc Queudot · Mar 10, 2026 · Citations: 0
Demonstrations
We evaluate this framework on the BioASQ and PubMedQA benchmarks, specifically analyzing the impact of dynamic in-context learning and rerank- ing under constrained token budgets.
- The Generation-Recognition Asymmetry: Six Dimensions of a Fundamental Divide in Formal Language Theory
Romain Peyrichou · Mar 10, 2026 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- The Prediction-Measurement Gap: Toward Meaning Representations as Scientific Instruments
Hubert Plisiecki · Mar 10, 2026 · Citations: 0
- Lost in the Middle at Birth: An Exact Theory of Transformer Position Bias
Borun D Chowdhury · Mar 10, 2026 · Citations: 0
- CLIPO: Contrastive Learning in Policy Optimization Generalizes RLVR
Sijia Cui, Pengyu Cheng, Jiajun Song, Yongbo Gai, Guojun Zhang · Mar 10, 2026 · Citations: 0
- Hardware Efficient Approximate Convolution with Tunable Error Tolerance for CNNs
Vishal Shashidhar, Anupam Kumari, Roy P Paily · Mar 10, 2026 · Citations: 0
- From Data Statistics to Feature Geometry: How Correlations Shape Superposition
Lucas Prieto, Edward Stevinson, Melih Barsbey, Tolga Birdal, Pedro A. M. Mediano · Mar 10, 2026 · Citations: 0
- CREATE: Testing LLMs for Associative Creativity
Manya Wadhwa, Tiasa Singha Roy, Harvey Lederman, Junyi Jessy Li, Greg Durrett · Mar 10, 2026 · Citations: 0
- Understanding the Use of a Large Language Model-Powered Guide to Make Virtual Reality Accessible for Blind and Low Vision People
Jazmin Collins, Sharon Y Lin, Tianqi Liu, Andrea Stevenson Won, Shiri Azenkot · Mar 10, 2026 · Citations: 0
- Emotional Modulation in Swarm Decision Dynamics
David Freire-Obregón · Mar 10, 2026 · Citations: 0
- BEACON: Language-Conditioned Navigation Affordance Prediction under Occlusion
Xinyu Gao, Gang Chen, Javier Alonso-Mora · Mar 10, 2026 · Citations: 0
Web Browsing
As a result, they struggle to infer target locations in occluded regions, typically caused by furniture or moving humans.
- Think Before You Lie: How Reasoning Leads to Honesty
Ann Yuan, Asma Ghandeharioun, Carter Blum, Alicia Machado, Jessica Hoffmann · Mar 10, 2026 · Citations: 0
- Towards a Neural Debugger for Python
Maximilian Beck, Jonas Gehring, Jannik Kossen, Gabriel Synnaeve · Mar 10, 2026 · Citations: 0
- When Learning Rates Go Wrong: Early Structural Signals in PPO Actor-Critic
Alberto Fernández-Hernández, Cristian Pérez-Corral, Jose I. Mestre, Manuel F. Dolz, Jose Duato · Mar 10, 2026 · Citations: 0
- The Confidence Gate Theorem: When Should Ranked Decision Systems Abstain?
Ronald Doku · Mar 10, 2026 · Citations: 0
- No Image, No Problem: End-to-End Multi-Task Cardiac Analysis from Undersampled k-Space
Yundi Zhang, Sevgi Gokce Kafali, Niklas Bubeck, Daniel Rueckert, Jiazhen Pan · Mar 10, 2026 · Citations: 0
- PathMem: Toward Cognition-Aligned Memory Transformation for Pathology MLLMs
Jinyue Li, Yuci Liang, Qiankun Li, Xinheng Lyu, Jiayu Qian · Mar 10, 2026 · Citations: 0
- Towards Flexible Spectrum Access: Data-Driven Insights into Spectrum Demand
Mohamad Alkadamani, Amir Ghasemi, Halim Yanikomeroglu · Mar 10, 2026 · Citations: 0
- Model Merging in the Era of Large Language Models: Methods, Applications, and Future Directions
Mingyang Song, Mao Zheng · Mar 10, 2026 · Citations: 0
We further examine downstream applications across multi-task learning, safety alignment, domain specialization, and federated learning, and survey the supporting ecosystem of tools and evaluation benchmarks.
- Adaptive Clinical-Aware Latent Diffusion for Multimodal Brain Image Generation and Missing Modality Imputation
Rong Zhou, Houliang Zhou, Yao Su, Brian Y. Chen, Yu Zhang · Mar 10, 2026 · Citations: 0
- AI-Enabled Data-driven Intelligence for Spectrum Demand Estimation
Colin Brown, Mohamad Alkadamani, Halim Yanikomeroglu · Mar 10, 2026 · Citations: 0
- MedMASLab: A Unified Orchestration Framework for Benchmarking Multimodal Medical Multi-Agent Systems
Yunhang Qian, Xiaobin Hu, Jiaquan Yu, Siyang Xin, Xiaokun Chen · Mar 10, 2026 · Citations: 0
Multi Agent
While Multi-Agent Systems (MAS) show potential for complex clinical decision support, the field remains hindered by architectural fragmentation and the lack of standardized multimodal integration.
- Thinking to Recall: How Reasoning Unlocks Parametric Knowledge in LLMs
Zorik Gekhman, Roee Aharoni, Eran Ofek, Mor Geva, Roi Reichart · Mar 10, 2026 · Citations: 0
- MSSR: Memory-Aware Adaptive Replay for Continual LLM Fine-Tuning
Yiyang Lu, Yu He, Jianlong Chen, Hongyuan Zha · Mar 10, 2026 · Citations: 0
- Influencing LLM Multi-Agent Dialogue via Policy-Parameterized Prompts
Hongbo Bo, Jingyu Hu, Weiru Liu · Mar 10, 2026 · Citations: 0
Multi Agent
Large Language Models (LLMs) have emerged as a new paradigm for multi-agent systems.
- LCA: Local Classifier Alignment for Continual Learning
Tung Tran, Danilo Vasconcellos Vargas, Khoat Than · Mar 10, 2026 · Citations: 0
- Benchmarking Political Persuasion Risks Across Frontier Large Language Models
Zhongren Chen, Joshua Kalla, Quan Le · Mar 10, 2026 · Citations: 0
- Emerging Extrinsic Dexterity in Cluttered Scenes via Dynamics-aware Policy Learning
Yixin Zheng, Jiangran Lyu, Yifan Zhang, Jiayi Chen, Mi Yan · Mar 10, 2026 · Citations: 0
- Do What I Say: A Spoken Prompt Dataset for Instruction-Following
Maike Züfle, Sara Papi, Fabian Retkowski, Szymon Mazurek, Marek Kasztelnik · Mar 10, 2026 · Citations: 0
- N-gram-like Language Models Predict Reading Time Best
James A. Michaelov, Roger P. Levy · Mar 10, 2026 · Citations: 0
- A Graph-Based Approach to Spectrum Demand Prediction Using Hierarchical Attention Networks
Mohamad Alkadamani, Halim Yanikomeroglu, Amir Ghasemi · Mar 10, 2026 · Citations: 0
- SCENEBench: An Audio Understanding Benchmark Grounded in Assistive and Industrial Use Cases
Laya Iyer, Angelina Wang, Sanmi Koyejo · Mar 10, 2026 · Citations: 0
- Chow-Liu Ordering for Long-Context Reasoning in Chain-of-Agents
Naman Gupta, Vaibhav Singh, Arun Iyer, Kirankumar Shiragur, Pratham Grover · Mar 10, 2026 · Citations: 0
Multi Agent
Sequential multi-agent reasoning frameworks such as Chain-of-Agents (CoA) handle long-context queries by decomposing inputs into chunks and processing them sequentially using LLM-based worker agents that read from and update a bounded…
- MA-EgoQA: Question Answering over Egocentric Videos from Multiple Embodied Agents
Kangsan Kim, Yanlai Yang, Suji Kim, Woongyeong Yeo, Youngwan Lee · Mar 10, 2026 · Citations: 0
- One-Eval: An Agentic System for Automated and Traceable LLM Evaluation
Chengyu Shen, Yanheng Hou, Minghui Pan, Runming He, Zhen Hao Wong · Mar 10, 2026 · Citations: 0
- Correction of Transformer-Based Models with Smoothing Pseudo-Projector
Vitaly Bulgakov · Mar 10, 2026 · Citations: 0
- MITRA: An AI Assistant for Knowledge Retrieval in Physics Collaborations
Abhishikth Mallampalli, Sridhara Dasu · Mar 10, 2026 · Citations: 0
- Exploiting Adaptive Channel Pruning for Communication-Efficient Split Learning
Jialei Tan, Zheng Lin, Xiangming Cai, Ruoxi Zhu, Zihan Fang · Mar 10, 2026 · Citations: 0
- A Hybrid Quantum-Classical Framework for Financial Volatility Forecasting Based on Quantum Circuit Born Machines
Yixiong Chen · Mar 10, 2026 · Citations: 0
- Quantifying the Necessity of Chain of Thought through Opaque Serial Depth
Jonah Brown-Cohen, David Lindner, Rohin Shah · Mar 10, 2026 · Citations: 0
- EPIC-EuroParl-UdS: Information-Theoretic Perspectives on Translation and Interpreting
Maria Kunilovskaya, Christina Pollkläsener · Mar 10, 2026 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- First Estimation of Model Parameters for Neutrino-Induced Nucleon Knockout Using Simulation-Based Inference
Karla Tame-Narvaez, Steven Gardiner, Aleksandra Ćiprijanović, Giuseppe Cerati · Mar 10, 2026 · Citations: 0
- World2Mind: Cognition Toolkit for Allocentric Spatial Reasoning in Foundation Models
Shouwei Ruan, Bin Wang, Zhenyu Wu, Qihui Zhu, Yuxiang Zhang · Mar 10, 2026 · Citations: 0
- Ego: Embedding-Guided Personalization of Vision-Language Models
Soroush Seifi, Simon Gardier, Vaggelis Dorovatas, Daniel Olmeda Reino, Rahaf Aljundi · Mar 10, 2026 · Citations: 0
- Beyond Fine-Tuning: Robust Food Entity Linking under Ontology Drift with FoodOntoRAG
Jan Drole, Ana Gjorgjevikj, Barbara Korouši'c Seljak, Tome Eftimov · Mar 10, 2026 · Citations: 0
- EXPLORE-Bench: Egocentric Scene Prediction with Long-Horizon Reasoning
Chengjun Yu, Xuhan Zhu, Chaoqun Du, Pengfei Yu, Wei Zhai · Mar 10, 2026 · Citations: 0
Long Horizon
Multimodal large language models (MLLMs) are increasingly considered as a foundation for embodied agents, yet it remains unclear whether they can reliably reason about the long-term physical consequences of actions from an egocentric…
- RbtAct: Rebuttal as Supervision for Actionable Review Feedback Generation
Sihong Wu, Yiling Ma, Yilun Zhao, Tiansheng Hu, Owen Jiang · Mar 10, 2026 · Citations: 0
- AutoAgent: Evolving Cognition and Elastic Memory Orchestration for Adaptive Agents
Xiaoxing Wang, Ning Liao, Shikun Wei, Chen Tang, Feiyu Xiong · Mar 10, 2026 · Citations: 0
- Does the Question Really Matter? Training-Free Data Selection for Vision-Language SFT
Peng Sun, Huawen Shen, Yi Ban, Tianfan Fu, Yanbo Wang · Mar 10, 2026 · Citations: 0
- MUGEN: Evaluating and Improving Multi-audio Understanding of Large Audio-Language Models
Chih-Kai Yang, Yun-Shao Tsai, Yu-Kai Guo, Ping-Le Tsai, Yen-Ting Piao · Mar 10, 2026 · Citations: 0