cs.AI papers | Gist.Science

Effective Resistance Rewiring: A Simple Topological Correction for Over-Squashing

This paper introduces Effective Resistance Rewiring (ERR), a parameter-free topological correction method that iteratively optimizes graph connectivity by adding and removing edges based on global effective resistance to alleviate over-squashing in Graph Neural Networks, while demonstrating that combining this approach with normalization techniques effectively balances the trade-off between improved long-range signal propagation and oversmoothing.

Bertran Miquel-Oliver, Manel Gil-Sorribes, Victor Guallar, Alexis Molina2026-03-13🤖 cs.LG

Geometry-Aware Probabilistic Circuits via Voronoi Tessellations

This paper proposes integrating Voronoi tessellations into probabilistic circuits to capture local data geometry, addressing the resulting tractability challenges through both an approximate inference framework with guaranteed bounds and a structural condition for exact inference, while enabling gradient-based learning via a differentiable relaxation.

Sahil Sidheekh, Sriraam Natarajan2026-03-13🤖 cs.LG

Delayed Backdoor Attacks: Exploring the Temporal Dimension as a New Attack Surface in Pre-Trained Models

This paper introduces Delayed Backdoor Attacks (DBA), a novel threat paradigm that decouples trigger exposure from malicious activation via a temporal dimension, enabling the use of common words as triggers and demonstrating the feasibility of the DND prototype which remains dormant before achieving near-perfect attack success rates while evading current defenses.

Zikang Ding, Haomiao Yang, Meng Hao, Wenbo Jiang, Kunlan Xiang, Runmeng Du, Yijing Liu, Ruichen Zhang, Dusit Niyato2026-03-13🤖 cs.AI

Learning Transferable Sensor Models via Language-Informed Pretraining

This paper introduces SLIP, an open-source framework that leverages language-informed pretraining with a flexible patch-embedder and cross-attention mechanism to learn transferable sensor representations capable of handling diverse configurations and achieving superior zero-shot performance in classification, captioning, and question answering across 11 datasets.

Yuliang Chen, Arvind Pillai, Yu Yvonne Wu, Tess Z. Griffin, Lisa Marsch, Michael V. Heinz, Nicholas C. Jacobson, Andrew Campbell2026-03-13🤖 cs.AI

Multimodal Emotion Recognition via Bi-directional Cross-Attention and Temporal Modeling

This paper proposes a multimodal emotion recognition framework for the ABAW 10th EXPR challenge that combines frozen CLIP and Wav2Vec 2.0 backbones with temporal convolutional networks and a bi-directional cross-attention fusion module to achieve robust performance in unconstrained real-world environments.

Junhyeong Byeon, Jeongyeol Kim, Sejoon Lim2026-03-13🤖 cs.AI

Normative Common Ground Replication (NormCoRe): Replication-by-Translation for Studying Norms in Multi-agent AI

This paper introduces NormCoRe, a novel methodological framework that systematically translates human subject experiments into multi-agent AI environments to study normative coordination, demonstrating through a distributive justice replication that AI agents' normative judgments differ from human baselines and are sensitive to foundation model and persona choices.

Luca Deck, Simeon Allmendinger, Lucas Müller, Niklas Kühl2026-03-13🤖 cs.AI

HomeSafe-Bench: Evaluating Vision-Language Models on Unsafe Action Detection for Embodied Agents in Household Scenarios

This paper introduces HomeSafe-Bench, a comprehensive benchmark for evaluating unsafe action detection in household scenarios using 438 diverse cases, and proposes HD-Guard, a hierarchical dual-brain architecture that effectively balances real-time inference efficiency with deep multimodal reasoning safety monitoring.

Jiayue Pu, Zhongxiang Sun, Zilu Zhang, Xiao Zhang, Jun Xu2026-03-13🤖 cs.AI

LABSHIELD: A Multimodal Benchmark for Safety-Critical Reasoning and Planning in Scientific Laboratories

This paper introduces LABSHIELD, a multimodal benchmark grounded in OSHA and GHS standards that evaluates the safety awareness and reasoning capabilities of large language models in laboratory settings, revealing a significant performance gap in hazard identification and safety-critical planning compared to general-domain tasks.

Qianpu Sun, Xiaowei Chi, Yuhan Rui, Ying Li, Kuangzhi Ge, Jiajun Li, Sirui Han, Shanghang Zhang2026-03-13🤖 cs.AI

BTZSC: A Benchmark for Zero-Shot Text Classification Across Cross-Encoders, Embedding Models, Rerankers and LLMs

This paper introduces BTZSC, a comprehensive benchmark of 22 datasets designed to systematically evaluate and compare the zero-shot text classification capabilities of NLI cross-encoders, embedding models, rerankers, and instruction-tuned LLMs, revealing that modern rerankers currently achieve state-of-the-art performance while embedding models offer the best accuracy-latency trade-off.

Ilias Aarab2026-03-13💬 cs.CL

Few-for-Many Personalized Federated Learning

This paper introduces FedFew, a personalized federated learning framework that reformulates the problem as a few-for-many optimization task to efficiently serve thousands of heterogeneous clients with only a few shared server models, achieving near-optimal personalization without manual clustering or hyperparameter tuning.

Ping Guo, Tiantian Zhang, Xi Lin, Xiang Li, Zhi-Ri Tang, Qingfu Zhang2026-03-13🤖 cs.AI

Can RL Improve Generalization of LLM Agents? An Empirical Study

This paper empirically demonstrates that while Reinforcement Fine-Tuning (RFT) enables LLM agents to generalize well across varying task difficulties within a single environment, it struggles with cross-environment transfer due to interface and semantic shifts, though sequential and mixture training strategies can effectively mitigate forgetting and improve overall generalization.

Zhiheng Xi, Xin Guo, Jiaqi Liu, Jiazheng Zhang, Yutao Fan, Zhihao Zhang, Shichun Liu, Mingxu Chai, Xiaowei Shi, Yitao Zhai, Xunliang Cai, Tao Gui, Qi Zhang, Xuanjing Huang2026-03-13🤖 cs.AI

Flowcean - Model Learning for Cyber-Physical Systems

Flowcean is a novel, modular framework that automates the data-driven generation and evaluation of Cyber-Physical System models by integrating diverse learning strategies and tools to enhance efficiency and accessibility.

Maximilian Schmidt, Swantje Plambeck, Markus Knitt, Hendrik Rose, Goerschwin Fey, Jan Christian Wieck, Stephan Balduin2026-03-13🤖 cs.LG

An Intent of Collaboration: On Agencies between Designers and Emerging (Intelligent) Technologies

This paper argues that to maintain creative agency while collaborating with emerging intelligent technologies like LLMs, designers must engage in introspection, develop a structural understanding of the technology's capabilities, and deliberately adjust the human-technology working relationship.

Pei-Ying Lin, Julie Heij, Iris Borst, Britt Joosten, Kristina Andersen, Wijnand IJsselsteijn2026-03-13🤖 cs.AI

Sim-to-reality adaptation for Deep Reinforcement Learning applied to an underwater docking application

This paper presents a systematic sim-to-reality adaptation framework using a high-fidelity Stonefish digital twin and PPO-based Deep Reinforcement Learning to achieve over 90% successful autonomous docking for the Girona AUV, validated by physical experiments demonstrating emergent control behaviors.

Alaaeddine Chaarani, Narcis Palomeras, Pere Ridao2026-03-13🤖 cs.AI

Just Use XML: Revisiting Joint Translation and Label Projection

This paper introduces LabelPigeon, a novel framework that uses XML tags to jointly perform machine translation and label projection, demonstrating that this approach not only outperforms existing baselines in cross-lingual transfer tasks but also actively improves translation quality across multiple languages.

Thennal D K, Chris Biemann, Hans Ole Hatzel2026-03-13💬 cs.CL

Cascade: Composing Software-Hardware Attack Gadgets for Adversarial Threat Amplification in Compound AI Systems

This paper introduces "Cascade," a framework demonstrating how traditional software and hardware vulnerabilities can be composed with LLM-specific algorithmic weaknesses to amplify adversarial threats and compromise the integrity and confidentiality of compound AI systems.

Sarbartha Banerjee, Prateek Sahu, Anjo Vahldiek-Oberwagner, Jose Sanchez Vicarte, Mohit Tiwari2026-03-13🤖 cs.AI

Slow-Fast Inference: Training-Free Inference Acceleration via Within-Sentence Support Stability

The paper proposes Slow-Fast Inference (SFI), a training-free framework that accelerates long-context autoregressive decoding by dynamically alternating between low-cost fast steps using stable sparse memory and occasional slow steps that refresh context at semantic boundaries, achieving significant throughput gains without compromising generation quality.

Xingyu Xie, Zhaochen Yu, Yue Liao, Tao Wang, Kim-Chuan Toh, Shuicheng Yan2026-03-13🤖 cs.LG

XSkill: Continual Learning from Experience and Skills in Multimodal Agents

XSkill is a dual-stream framework that enables multimodal agents to continually improve their reasoning and tool orchestration in open-ended settings without parameter updates by extracting and retrieving complementary visual-grounded knowledge in the form of action-level experiences and task-level skills.

Guanyu Jiang (May), Zhaochen Su (May), Xiaoye Qu (May), Yi R. (May), Fung2026-03-13🤖 cs.AI

Coarse-Guided Visual Generation via Weighted h-Transform Sampling

This paper proposes a novel training-free method for coarse-guided visual generation that leverages the h-transform to steer diffusion model sampling toward high-fidelity outputs from low-quality references, utilizing a noise-level-aware schedule to balance guidance adherence with synthesis quality without requiring knowledge of the forward transformation operator.

Yanghao Wang, Ziqi Jiang, Zhen Wang, Long Chen2026-03-13🤖 cs.AI

Chemical Reaction Networks Learn Better than Spiking Neural Networks

This paper mathematically proves and numerically demonstrates that chemical reaction networks without hidden layers can outperform spiking neural networks with hidden layers in learning classification tasks, offering a theoretical foundation for efficient learning in chemical computers and biological cells.

Sophie Jaffard, Ivo F. Sbalzarini2026-03-13📊 stat

← Previous Next →