Key papers

• $\mathbf{\lambda}$-VAE: Variance Equalization for Posterior Collapse (2026)
  Girum Demisse
  4.39
• How Query Visibility Changes KV-Cache Compression Rankings: A Matched-Budget Audit (2026)
  Daming Luo et al.
  4.39
• LiteTopK: Exploiting the Curse of Dimensionality for a Fused Indexer-TopK Kernel in Long-Context Sparse Attention (2026)
  Ziqi Yin et al.
  4.39
• From Geometric Recovery to Causal Validation: A Reproducible Audit of Sparse Autoencoder Features, from Superposition Geometry to Causal Inertness (2026)
  Mohamed Abdessalem Bal
  4.39
• What Makes a Representational Prior Work? Feature Families, Label-Free Invariances, and Critical Windows in Grokking (2026)
  Gunner Levi Howe
  4.39
• Variance-Preserving Orthogonal Selection (VPOS): Greedy Feature Selection via Orthogonal Deflation in PCA Loading Space (2026)
  Baran Koseoglu et al.
  4.39
• Boosting with List-Decodable Codes (2026)
  Addison Prairie et al.
  3.51
• Remembering Distinct Items, Not Tokens: A Learnable Dirichlet-Process Cache Between State-Space Models and Attention (2026)
  Siddharth Pal et al.
  3.51
• TAKE: Trajectory-Aware Knowledge Estimation for Text Dataset Distillation (2026)
  Tri-Nhan Vo et al.
  3.51
• Transforming LLMs into Efficient Cross-Encoders via Knowledge Distillation for RAG Reranking (2026)
  Shreeya Dasa Lakshminath et al.
  3.51
• SlimPer: Make Personalization Model Slim and Smart (2026)
  Siqi Wang et al.
  3.51
• ScoreShield: Differentially Private Release of Similarity Scores (2026)
  Behrooz Razeghi et al.
  3.51
• Structure-Specific Representational Priors Causally Control the Grokking Delay (2026)
  Gunner Levi Howe
  2.00
• Do All Visual Tokens Matter Equally? Object-Evidence Preserving Token Merging for Vision-Language Retrieval (2026)
  Suhyeong Park et al.
  2.00
• AnchorPrune: Relevance-Anchored Contextual Expansion for Visual Token Pruning (2026)
  Kyuan Oh et al.
  2.00
• Tokenizing Numerical and Embedding Features for LLM RecSys (2026)
  Zhe Xu et al.
  2.00
• RDQ: Residual Distribution Quantization for Large Language Models (2026)
  Prateek Singh
  2.00
• A VAE-Driven Multi-Task Satellite-Aided Semantic Communication Framework for 6G-Enabled Connected Autonomous Vehicles (2026)
  S. M. Abtahiul Alam et al.
  2.00
• RoCo-ACE: Rollout-Conditioned Online Distillation for Retention-Aware Knowledge Injection (2026)
  Yan Hong et al.
  2.00
• JKO-RAG: Distributional Retrieval as Wasserstein Free-Energy Gradient Flow (2026)
  Levi Segal et al.
  2.00
• Three Sides of Retrieval: Factorial Evidence for Document-Side, Query-Side, and Answer-Side Complementarity in RAG (2026)
  Ng S. T. Chong
  2.00
• SpecPrefetch: Parameter-Efficient Expert Prefetching for Sparse MoE Foundation Models (2026)
  Jinwei Kong et al.
  2.00
• GLIDE: Guided Layerwise Hybrid Attention for Efficient LLM Inference (2026)
  Vimal William et al.
  2.00
• Bumblebee: Interleaved Mixed-Layer Building Blocks for Large-Scale Recommendation Systems (2026)
  David Bauer et al.
  2.00
• Forgetting Is Not a Fix: Path Dependence in Sequential Engram Editing (2026)
  Ferdinand M. Schessl
  2.00
• Stronger Memory-Query Tradeoffs for Convex Optimization: The Limitations of Subquadratic Memory (2026)
  Michael Menart et al.
  2.00
• REPREC: Representation Driven Parameter-Efficient Recommendation System (2026)
  Harshini Kavuru et al.
  2.00
• Tokens are All You Need: Dual-purpose Semantic IDs for Achieving LLM-Level I/O Efficiency in recommendation systems (2026)
  Baolei Li et al.
  2.00
• Ranked by Position: Order Sensitivity as an Exploitable Attack Surface in LLM Listwise Recommenders (2026)
  Ge Zhang et al.
  2.00
• Multiclass Classification without Labels via Posterior Simplex Geometry (2026)
  Rapha\"el Bonnet-Guerrini et al.
  2.00
• Stable FP4 Training via Transposition-Invariant Block Quantization (2026)
  Mehdi Rahimifar et al.
  2.00
• Understanding Semantic IDs: From Item Representation to Item Selection in Generative Recommendation (2026)
  Junting Wang et al.
  2.00
• Spectral Truncation in Synthetic Control (2026)
  Mojtaba Eslami
  2.00
• Memory Layer: Train the In-Model Cache for Recommendation Models (2026)
  Liangyuan Na et al.
  2.00
• Endpoint Replay: Compressing the Recency Buffer in Deep Reinforcement Learning (2026)
  Parham Mohammad Panahi et al.
  2.00
• ScalableRAG: High-Quality RAG at Zero Ingestion Cost (2026)
  Hilaf Hasson et al.
  2.00
• Lloyd's $K$-Means Clustering Algorithm Is Frank-Wolfe in Disguise (2026)
  Michael Pokojovy et al.
  2.00
• VaLiDRec: Variable-Length LLM-Aligned Semantic IDs for Generative Recommendation (2026)
  Shutong Qiao et al.
  2.00
• TopoGR: Revealing and Preserving Latent Structure of Semantic ID in Generative Recommendation (2026)
  Ziyu Zheng et al.
  2.00
• FORGE: Frame Orthogonality in Relevance Geometry for Long-Form Video Understanding (2026)
  Ghazal Kaviani et al.
  2.00
• Structure-aware Relative Policy Optimization for Ranking (2026)
  Yiteng Tu et al.
  2.00
• Bridging Compute- and Data-Optimal Pretraining (2026)
  Tian Qin et al.
  2.00
• Breaking the Periodicity Assumption: Robust Tensorial Multi-View Clustering via Graph-Spectral Low-Rank Learning (2026)
  Jintian Ji et al.
  2.00
• Every Time I Hire a Linguist, Inference Costs Go Down: On Linguistic Rules as Effective Prompt Compressors (2026)
  Jianfei Ma et al.
  2.00
• Raven: High-Recall Sequence Modeling with Sparse Memory Routing (2026)
  Arshia Afzal et al.
  2.00
• Sharpness-aware Model Merging with Salience Recovery for LLM-based Cross-Domain Sequential Recommendation (2026)
  Huwei Ji et al.
  2.00
• TWICE: Two-Clock, Two-Window Learning for Long-Horizon Conversion Prediction in Online Advertising (2026)
  Kaiyuan Li et al.
  2.00
• Salient Knowledge Pathways: Sparse Cross-Modal Routing for Efficient Knowledge-Intensive Multimodal Question Answering (2026)
  Noor Islam S. Mohammad et al.
  2.00
• Seen, Said, or Forgotten? A Causal Audit of Visual KV Memory Across Dialog Turns (2026)
  Hong Chen et al.
  2.00
• Balancing multiscale similarity and cartographic constraints: A similarity-driven optimization framework for line generalization (2026)
  Pengbo Li et al.
  2.00
• Anti-Backdoor Coreset Selection via Cumulative Entropy (2026)
  Qi Zhao et al.
  2.00
• At-the-Roofline Sparse Tensor Contractions on Vector Processors for Transformer Inference (2026)
  Bowen Wang et al.
  2.00
• ReLATE: Reliability-Guided Evidence Fusion for Robust UAV--Satellite cross-view Geo-Localization (2026)
  Haochen Jiang et al.
  2.00
• Less is More: Modality-Decoupling for General AIGC Audio-Video Detection (2026)
  Jielun Peng et al.
  2.00
• OrthKD: Extracting Generalized Clinical Knowledge from Heterogeneous Teachers for Lightweight Deployment (2026)
  Yi Xu et al.
  2.00
• How Small Can You Go? A Controlled Study of LoRA Rank, Target Modules, and Quantization Trade-offs for Text-to-SQL on a 60M-Parameter Model (2026)
  Mahendra Singh Rathor et al.
  2.00
• Contextual Deconvolution for Variance-Stable Demand Sensing: Kernel-Modulated Operators in Promotional Retail (2026)
  Mohammad Forouhesh
  2.00
• OmniDelta: Skill-Driven Budget Allocation for Token Compression in OmniLLMs (2026)
  Haoyang Huang et al.
  2.00
• Loss Invariance Determines What Concept Layers Encode: Volume Grounding in Echocardiography (2026)
  Hyunkyung Han et al.
  2.00
• VAD to the Bone: Ultra-Tiny Speech Activity Detection for Edge Deployment (2026)
  Stephen Bauer et al.
  2.00