arXiv:2605.27407v1 Announce Type: cross Abstract: Evaluating fairness in Spiking Neural Networks (SNNs) demands rigorous benchmarks that reflect real-world complexities, yet existing assessments remain limited by superficial dataset diversity and idealized hardware assumptions. This work introduces the first systematic fairness benchmark for SNNs, addressing three critical dimensions of realism: (1) demographic coverage gaps in training data, […]
Multi-Teacher Knowledge Distillation via Teacher-Informed Mixture Priors
arXiv:2605.27967v1 Announce Type: cross Abstract: Knowledge distillation is a powerful method for model compression, enabling the efficient deployment of complex deep learning models (teachers), including large language models. However, its underlying statistical mechanisms remain unclear, and uncertainty evaluation is often overlooked, especially in real-world scenarios requiring diverse teacher expertise. To address these challenges, we introduce […]
Checking Fact with Better Retrieval: Dynamic Contrastive Learning for Evidence Retrieval
arXiv:2605.27449v1 Announce Type: cross Abstract: In the field of multimodal fact checking, the accuracy of retrieving evidence from different modalities has a significant impact on the downstream claim verification process. Existing general multimodal retrieval methods are often constructed based on semantics, resulting in the retrieved evidence being similar but not relevant to the claim. This […]
TABX: A High-Throughput Sandbox Battle Simulator for Multi-Agent Reinforcement Learning
arXiv:2602.01665v4 Announce Type: replace-cross Abstract: The design of environments plays a critical role in shaping the development and evaluation of cooperative multi-agent reinforcement learning (MARL) algorithms. While existing benchmarks highlight critical challenges, they often lack the modularity required to design custom evaluation scenarios. We introduce the Totally Accelerated Battle Simulator in JAX (TABX), a high-throughput […]
AlphaTransit: Learning to Design City-scale Transit Routes
arXiv:2605.28730v1 Announce Type: new Abstract: Designing a transit network requires many sequential route extension decisions, but their quality is often visible only after the full network is assembled. This delayed-feedback challenge lies at the heart of the Transit Route Network Design Problem (TRNDP), where route interactions can be deceptive: an extension that appears useful locally […]
KT4EQG: Personalized Exercise Question Generation via Knowledge Tracing
arXiv:2605.23933v2 Announce Type: replace-cross Abstract: Educational Question Generation (EQG) aims to synthesize customized exercise questions that enhance student learning. An effective EQG system should ideally personalize questions for each student by modeling the student’s knowledge state and generating questions that provide the greatest learning benefit. However, few existing EQG approaches are able to achieve such […]
Personalized Observation Normalization for Federated Reinforcement Learning in Simulation Environments with Heterogeneity
arXiv:2605.27385v1 Announce Type: cross Abstract: Federated reinforcement learning (FedRL) enables multiple agents to collaboratively train a global policy without sharing raw data, making it ideal for privacy-sensitive applications. However, FedRL faces challenges in heterogeneous environments where differing state-transition dynamics lead to non-identical input distributions and imbalanced parameter updates during aggregation. Therefore, this paper develops a […]
Beyond Model Ranking: Predictability-Aligned Evaluation for Time Series Forecasting
arXiv:2509.23074v3 Announce Type: replace-cross Abstract: In the era of increasingly complex AI models for time series forecasting, progress is often measured by marginal improvements on benchmark leaderboards. However, this approach suffers from a fundamental flaw: standard evaluation metrics conflate a model’s performance with the data’s intrinsic unpredictability. To address this pressing challenge, we introduce a […]
ROVER: Routing Object-Centric Visual Evidence for Grounded Multi-Image Reasoning
arXiv:2605.27959v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have increasingly localized and interleaved visual evidence for deliberative reasoning. Grounding-based approaches typically focus on regions of interest (RoIs) by injecting cropped image patches or RoI-specific features into the reasoning context. However, such designs can weaken holistic scene understanding and inter-object relations, while incurring decoding […]
Where Does Toxicity Live? Mechanistic Localization and Targeted Suppression in Language Models
arXiv:2605.27997v1 Announce Type: cross Abstract: Large language models frequently generate toxic, hateful, or harmful content, yet existing mitigation methods rely on costly retraining or output-level filtering with no mechanistic insight into where toxicity originates internally. We introduce Meow2X and TRNE, two complementary retraining-free frameworks that localize toxicity to specific layers and neurons by analyzing activation […]
SAME: Stabilized Mixture-of-Experts for Multimodal Continual Instruction Tuning
arXiv:2602.01990v2 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) achieve strong performance through instruction tuning, but real-world deployment requires them to continually expand their capabilities, making Multimodal Continual Instruction Tuning (MCIT) essential. Recent methods leverage sparse expert routing to promote task specialization, but we find that the expert routing process suffers from drift as […]
Case-Aware Medical Image Classification with Multimodal Knowledge Graphs and Reliability-Guided Refinement
arXiv:2605.22547v2 Announce Type: replace-cross Abstract: Deep learning has brought significant progress to medical image classification, yet most existing methods still rely on isolated visual evidence and cannot effectively leverage similar cases or external knowledge. In clinical practice, diagnosis is typically supported by similar historical cases and their associated symptoms. To explicitly model this evidence-based diagnostic […]