🤖 Category

cs.LG

7420 papers

CARE What Fails: Contrastive Anchored-REflection for Verifiable Multimodal

CARE (Contrastive Anchored REflection) is a failure-centric post-training framework for multimodal reasoning that enhances Group-relative Reinforcement Learning with Verifiable Rewards (RLVR) by leveraging an anchored-contrastive objective and Reflection-Guided Resampling to transform erroneous rollouts into effective supervision signals, thereby significantly improving accuracy and training stability on visual-reasoning benchmarks.

Yongxin Wang, Zhicheng Yang, Meng Cao, Mingfei Han, Haokun Lin, Yingying Zhu, Xiaojun Chang, Xiaodan Liang2026-03-09🤖 cs.AI

LLMTM: Benchmarking and Optimizing LLMs for Temporal Motif Analysis in Dynamic Graphs

This paper introduces LLMTM, a comprehensive benchmark for evaluating Large Language Models on temporal motif analysis in dynamic graphs, and proposes a cost-effective, structure-aware dispatcher that intelligently balances high accuracy and computational expense by routing queries between standard prompting and a specialized tool-augmented agent.

Bing Hao, Minglai Shao, Zengyi Wo, Yunlong Chu, Yuhang Liu, Ruijie Wang2026-03-09🤖 cs.AI

Purification Before Fusion: Toward Mask-Free Speech Enhancement for Robust Audio-Visual Speech Recognition

This paper proposes a novel end-to-end audio-visual speech recognition framework that integrates speech enhancement via a Conformer-based bottleneck fusion module to implicitly refine noisy audio features without explicit mask generation, thereby preserving semantic integrity and outperforming existing mask-based methods on the LRS3 benchmark under noisy conditions.

Linzhi Wu, Xingyu Zhang, Hao Yuan, Yakun Zhang, Changyan Zheng, Liang Xie, Tiejun Liu, Erwei Yin2026-03-09🤖 cs.AI

Beyond Mapping : Domain-Invariant Representations via Spectral Embedding of Optimal Transport Plans

This paper proposes a novel domain adaptation method that derives domain-invariant representations by interpreting smoothed optimal transport plans as bipartite graph adjacency matrices and applying spectral embedding, demonstrating strong performance across acoustic and electrical defect detection tasks while mitigating the sensitivity of traditional Monge map approximations to regularization and hyperparameters.

Abdel Djalil Sad Saoud, Fred Maurice Ngolè Mboula, Hanane Slimani2026-03-09🤖 cs.LG

Laser interferometry as a robust neuromorphic platform for machine learning

This paper presents a robust neuromorphic platform for machine learning that implements optical neural networks using only linear optical resources and coherent states, achieving necessary nonlinearity through phase-shift encoding to enable straightforward experimental in situ training and inference while demonstrating high resilience to photon losses.

Amanuel Anteneh, Kyungeun Kim, J. M. Schwarz, Israel Klich, Olivier Pfister2026-03-09🔬 physics.optics

Online unsupervised Hebbian learning in deep photonic neuromorphic networks

This paper presents and experimentally demonstrates a purely photonic deep neuromorphic network that achieves 100% accuracy on a letter recognition task by utilizing a local optical feedback mechanism with non-volatile phase-change material synapses to enable online, unsupervised Hebbian learning without inefficient optical-electrical-optical conversions.

Xi Li, Disha Biswas, Peng Zhou, Wesley H. Brigner, Anna Capuano, Joseph S. Friedman, Qing Gu2026-03-09🔬 physics.optics

Restoring Exploration after Post-Training: Latent Exploration Decoding for Large Reasoning Models

This paper introduces Latent Exploration Decoding (LED), a training-free decoding strategy that leverages high-entropy intermediate layer posteriors to counteract exploration collapse in post-trained Large Reasoning Models, thereby significantly improving accuracy across multiple benchmarks.

Wenhui Tan, Fiorenzo Parascandolo, Enver Sangineto, Jianzhong Ju, Zhenbo Luo, Qian Cao, Rita Cucchiara, Ruihua Song, Jian Luan2026-03-09🤖 cs.LG

Stress-Testing Alignment Audits With Prompt-Level Strategic Deception

This paper introduces an automatic red-team pipeline that successfully stress-tests alignment audits by generating strategic system prompts capable of deceiving both black-box and white-box methods into making confident, incorrect assessments of misaligned models, thereby revealing the first documented evidence of activation-based strategic deception.

Oliver Daniels, Perusha Moodley, Benjamin M. Marlin, David Lindner2026-03-09🤖 cs.LG

Towards Autonomous Mathematics Research

This paper introduces Aletheia, an autonomous AI research agent powered by advanced reasoning models and tool use that successfully generates, verifies, and revises mathematical proofs from Olympiad problems to PhD-level research, achieving milestones such as fully AI-generated papers and the autonomous solution of open problems while proposing new frameworks for quantifying AI autonomy and transparency.

Tony Feng, Trieu H. Trinh, Garrett Bingham, Dawsen Hwang, Yuri Chervonyi, Junehyuk Jung, Joonkyung Lee, Carlo Pagano, Sang-hyun Kim, Federico Pasqualotto, Sergei Gukov, Jonathan N. Lee, Junsu Kim, Kaiying Hou, Golnaz Ghiasi, Yi Tay, YaGuang Li, Chenkai Kuang, Yuan Liu, Hanzhao Lin, Evan Zheran Liu, Nigamaa Nayakanti, Xiaomeng Yang, Heng-Tze Cheng, Demis Hassabis, Koray Kavukcuoglu, Quoc V. Le, Thang Luong2026-03-09🤖 cs.AI

SWE-MiniSandbox: Container-Free Reinforcement Learning for Building Software Engineering Agents

SWE-MiniSandbox is a lightweight, container-free framework that leverages kernel-level isolation and environment pre-caching to significantly reduce storage and setup overhead while maintaining performance comparable to traditional container-based pipelines for scaling reinforcement learning in software engineering agents.

Danlong Yuan, Wei Wu, Zhengren Wang, Xueliang Zhao, Huishuai Zhang, Dongyan Zhao2026-03-09🤖 cs.AI

MiDAS: A Multimodal Data Acquisition System and Dataset for Robot-Assisted Minimally Invasive Surgery

This paper introduces MiDAS, an open-source, platform-agnostic system that enables non-invasive, time-synchronized multimodal data acquisition for robot-assisted minimally invasive surgery, validated by demonstrating that its external sensing approach achieves gesture recognition performance comparable to proprietary telemetry while releasing the first annotated dataset for hernia repair suturing.

Keshara Weerasinghe (MD), Seyed Hamid Reza Roodabeh (MD), Andrew Hawkins (MD), Zhaomeng Zhang, Zachary Schrader, Homa Alemzadeh2026-03-09🤖 cs.LG

An Adaptive Model Selection Framework for Demand Forecasting under Horizon-Induced Degradation to Support Business Strategy and Operations

This paper introduces AHSIV, an adaptive framework that addresses horizon-induced model ranking instability in demand forecasting by integrating horizon-aware error metrics, structural demand classification, and multi-objective optimization to provide robust, operationally coherent model selection for heterogeneous business environments.

Adolfo González, Víctor Parada2026-03-09🤖 cs.AI