{"total":29,"items":[{"citing_arxiv_id":"2606.28835","ref_index":45,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Fisher-Routed Mixture of Experts for Federated Class-Incremental Learning","primary_cat":"cs.LG","submitted_at":"2026-06-27T09:45:52+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"FedFMX adds Fisher-routed expert selection and routing-aware regularization to federated class-incremental learning and proves an O(T^{-1}) convergence rate.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.25700","ref_index":11,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Memory-Efficient Policy Libraries with Low-Rank Adaptation in Reinforcement Learning","primary_cat":"cs.LG","submitted_at":"2026-06-24T11:15:42+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"LoRA fine-tuning of PPO policies reduces memory use by 20-160x versus full updates, enabling 90-95% storage savings for libraries of 10-50 policies with no significant drop in task success.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.24985","ref_index":140,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Retrieval-Augmented Personalization with Foundation Models for Wearable Stress Detection","primary_cat":"cs.LG","submitted_at":"2026-06-23T14:24:43+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Retrieval from out-of-domain foundation models enables personalization of a lightweight transformer for stress detection, yielding +3.92% accuracy and +4.76% F1 gains on WESAD without user labels.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.22541","ref_index":35,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill","primary_cat":"cs.DC","submitted_at":"2026-06-21T14:57:45+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"ASAP is a disaggregated asynchronous inference system for the prefill phase of MoE models that removes DP-EP synchronization barriers and reports 90% higher SLO-compliant throughput than synchronous baselines.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.11867","ref_index":35,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Harnessing Routing Foresight for Micro-step-level MoE load balancing in RL Post-training","primary_cat":"cs.DC","submitted_at":"2026-06-10T09:42:11+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"ForeMoE uses routing foresight from the rollout stage to enable micro-step load balancing in MoE RL post-training via a hierarchical planner and transfer engine, claiming up to 1.45x speedup on 64 GPUs.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.09085","ref_index":40,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Mixture-of-Experts Transformer for Automatic Modulation Recognition","primary_cat":"eess.SP","submitted_at":"2026-06-08T06:32:41+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"MoEformer uses temporal resampling, input-dependent gating, and RoPE in a Transformer to achieve 63.74%, 66.24%, and 64.22% average accuracy on RadioML2016.10a, 2016.10b, and 2018.01A benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.01784","ref_index":9,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"MoRE: A Mixture-of-Experts-Based Task-Adaptive End-to-End Network for Multimodal MRI Reconstruction","primary_cat":"eess.IV","submitted_at":"2026-06-01T07:04:12+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"MoRE integrates a sparsely activated MoE module with unsupervised routing into a variational network for stable multimodal MRI reconstruction on fastMRI brain and knee data at 8x undersampling.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.01047","ref_index":24,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Learning Multi-Modal Trajectory Policies for Data-Efficient Robotic Manipulation","primary_cat":"cs.RO","submitted_at":"2026-05-31T06:35:10+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"MATE is a multi-modal MoE trajectory policy using a cosine router and stochastic noise to improve expert balance, reporting 4.75% higher average success rate than prior methods on LIBERO under data scarcity.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.00771","ref_index":8,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Logit Distillation on Manifolds: Mapping by Learning","primary_cat":"cs.LG","submitted_at":"2026-05-30T15:22:59+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"Presents a layer- and point-wise projection mapping for manifold-based logit distillation combined with LoRA to enable low-parameter student training with reported WER gains.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.31010","ref_index":28,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"MoG: Mixture of Experts for Graph-based Retrieval-Augmented Generation","primary_cat":"cs.CL","submitted_at":"2026-05-29T08:43:12+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"MoG uses hub graphs for shared context and sparsely activates expert graphs with a topology-aware router, reporting over 20% relative gains on MuSiQue.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.28070","ref_index":33,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Bridging the Detection-to-Abstention Gap in Reasoning Models under Insufficient Information","primary_cat":"cs.AI","submitted_at":"2026-05-27T07:28:25+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"JTS trains reasoning models via supervised warm-up and missing-premise RL to make an explicit answerability commitment that triggers early termination on unanswerable inputs, raising Abstention@Detection near saturation.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.26776","ref_index":57,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Towards Generalization-Oriented Models for Vehicle Routing Problems with Mixture-of-Experts","primary_cat":"cs.LG","submitted_at":"2026-05-26T09:46:54+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"R2E-IG combines residual refined experts with instance-level gating and mixed-distribution training using dynamic weight adaptation to improve generalization of DRL solvers for vehicle routing problems.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.24145","ref_index":91,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Inferring Neutron-Star Properties from Post-merger Gravitational-wave Spectra with Neural Networks","primary_cat":"gr-qc","submitted_at":"2026-05-22T19:07:00+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Neural networks trained on noise-free post-merger spectra outperform linear regression baselines at predicting neutron-star mass, quadrupolar tidal deformability, and mass-radius slope from numerical-relativity catalogs.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.20916","ref_index":12,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Task-Routed Mixture-of-Experts with Cognitive Appraisal for Implicit Sentiment Analysis","primary_cat":"cs.CL","submitted_at":"2026-05-20T08:59:32+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Task-routed mixture-of-experts with cognitive appraisal auxiliary tasks improves performance on implicit sentiment analysis.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.20610","ref_index":5,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Beyond Routing: Characterising Expert Tuning and Representation in Vision Mixture-of-Experts","primary_cat":"cs.CV","submitted_at":"2026-05-20T01:55:40+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Expert specialization in vision MoE models is dominated by a stable animate-inanimate distinction visible from gating to readout, with broader tuning to continuous visual and semantic dimensions rather than narrow categorical preferences.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.15403","ref_index":22,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"$\\phi$-Balancing for Mixture-of-Experts Training","primary_cat":"cs.LG","submitted_at":"2026-05-14T20:39:28+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"φ-balancing is a convex optimization method for population-level expert balance in MoE training that derives an online EMA adjustment and outperforms heuristic baselines.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.14200","ref_index":18,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"How to Scale Mixture-of-Experts: From muP to the Maximally Scale-Stable Parameterization","primary_cat":"cs.LG","submitted_at":"2026-05-13T23:32:00+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"The authors derive a Maximally Scale-Stable Parameterization (MSSP) for MoE models that achieves robust learning-rate transfer and monotonic performance gains with scale across co-scaling regimes of width, experts, and sparsity.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.13161","ref_index":28,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"A$_3$B$_2$: Adaptive Asymmetric Adapter for Alleviating Branch Bias in Vision-Language Image Classification with Few-Shot Learning","primary_cat":"cs.CV","submitted_at":"2026-05-13T08:24:55+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A3B2 introduces an adaptive asymmetric adapter with uncertainty-aware dampening to reduce branch bias in few-shot vision-language image classification and outperforms standard adapter and prompt methods.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.05927","ref_index":36,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Minimizing Modality Gap from the Input Side: Your Speech LLM Can Be a Prosody-Aware Text LLM","primary_cat":"cs.CL","submitted_at":"2026-05-07T09:32:05+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"TextPro-SLM reduces the speech-text modality gap by feeding an LLM backbone with synchronized text tokens and prosody embeddings from WhisperPro, achieving lowest gap scores at 3B/7B scales with roughly 1,000 hours of audio.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"[ 31] use Kullback-Leibler (KL) divergence to align the student's output on speech input with the teacher's output on text input. X-OPD [32] and CORD [33] extend this line with on-policy distillation, while Yanget al.[ 34] perform finer-grained layer-wise distillation. A separate line of work targets catastrophic forgetting during continual training on speech data: DeepOmni [35] uses a Mixture-of-Experts architecture [36] that separates text and speech experts, and Hsiaoet al.[ 37] identify experience replay as the most effective continual-learning strategy [ 38]. However, these methods mainly improve optimization and training stability rather than the interaction paradigm itself, which we view as a more fundamental source of the modality gap. 3 Methodology Our approach to minimizing the modality gap has two core components."},{"citing_arxiv_id":"2604.25376","ref_index":35,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"CoRE: Concept-Reasoning Expansion for Continual Brain Lesion Segmentation","primary_cat":"cs.CV","submitted_at":"2026-04-28T08:39:43+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"CoRE aligns image tokens to a hierarchical concept library to simulate clinical reasoning for expert routing and demand-based growth in continual brain lesion segmentation, achieving SOTA on 12 tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.16930","ref_index":26,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"CoGR-MoE: Concept-Guided Expert Routing with Consistent Selection and Flexible Reasoning for Visual Question Answering","primary_cat":"cs.CV","submitted_at":"2026-04-18T09:28:23+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"CoGR-MoE improves VQA by using concept-guided expert routing with option feature reweighting and contrastive learning to achieve consistent yet flexible reasoning across answer options.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.12005","ref_index":9,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"BayMOTH: Bayesian optiMizatiOn with meTa-lookahead -- a simple approacH","primary_cat":"cs.LG","submitted_at":"2026-04-13T19:52:08+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"BayMOTH unifies meta-Bayesian optimization with a usefulness-based fallback to lookahead, demonstrating competitive results on function optimization tasks even under low task relatedness.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.21493","ref_index":14,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Don't Collapse Your Features: Why CenterLoss Hurts OOD Detection and Multi-Scale Mahalanobis Wins","primary_cat":"cs.LG","submitted_at":"2026-04-10T18:27:46+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Avoiding CenterLoss improves OOD detection via multi-scale Mahalanobis on L2-normalized features, yielding 0.9483 AUROC on CIFAR-10 while preserving competitive in-distribution accuracy.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.04058","ref_index":145,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"MP-ISMoE: Mixed-Precision Interactive Side Mixture-of-Experts for Efficient Transfer Learning","primary_cat":"cs.LG","submitted_at":"2026-04-10T08:00:28+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"MP-ISMoE uses Gaussian noise perturbed iterative quantization and interactive side mixture-of-experts to deliver higher accuracy than prior memory-efficient transfer learning methods while keeping similar parameter and memory usage.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2603.24245","ref_index":24,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"B-MoE: A Body-Part-Aware Mixture-of-Experts \"All Parts Matter\" Approach to Micro-Action Recognition","primary_cat":"cs.CV","submitted_at":"2026-03-25T12:33:11+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"B-MoE framework achieves state-of-the-art performance on micro-action recognition by using region-specific experts and cross-attention routing.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2602.22457","ref_index":29,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"CCCL: Node-Spanning GPU Collectives with CXL Memory Pooling","primary_cat":"cs.DC","submitted_at":"2026-02-25T22:38:46+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"CCCL delivers 1.34-1.94x faster cross-node GPU collectives via CXL memory pooling than 200 Gbps InfiniBand RDMA, with 1.11x LLM training speedup and 2.75x hardware cost reduction.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2602.03204","ref_index":10,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Sparsity is Combinatorial Depth: Quantifying MoE Expressivity via Tropical Geometry","primary_cat":"cs.LG","submitted_at":"2026-02-03T07:17:38+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"MoE Top-k routing equals the k-th elementary symmetric tropical polynomial, making sparsity combinatorial depth that scales capacity by binom(N,k) and gives MoE combinatorial resilience on manifolds.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2601.20540","ref_index":51,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Advancing Open-source World Models","primary_cat":"cs.CV","submitted_at":"2026-01-28T12:37:01+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"LingBot-World is presented as an open-source world model that delivers high-fidelity simulation, minute-level contextual consistency, and real-time interactivity under one second latency.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2510.08008","ref_index":16,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Beyond Sunk Costs: Boosting LLM Pre-training Efficiency via Orthogonal Growth of Mixture-of-Experts","primary_cat":"cs.LG","submitted_at":"2025-10-09T09:45:45+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Orthogonal growth recycles pre-trained MoE checkpoints via layer copying and noisy expert duplication, delivering 10.6% higher accuracy than training from scratch with equivalent extra compute.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}