{"total":135,"rows":[{"id":"2605.29707","title":"Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding","created":"2026-05-28","cited_by_count":34,"area":"inference"},{"id":"2604.12989","title":"Accelerating Speculative Decoding with Block Diffusion Draft Trees","created":"2026-04-14","cited_by_count":29,"area":"inference"},{"id":"2604.08302","title":"DMax: Aggressive Parallel Decoding for dLLMs","created":"2026-04-09","cited_by_count":18,"area":"diffusion"},{"id":"2605.18810","title":"D-PACE: Dynamic Position-Aware Cross-Entropy for Parallel Speculative Drafting","created":"2026-05-12","cited_by_count":17,"area":"inference"},{"id":"2603.03251","title":"Speculative Speculative Decoding","created":"2026-03-03","cited_by_count":15,"area":"inference"},{"id":"2606.18394","title":"JetSpec: Breaking the Scaling Ceiling of Speculative Decoding with Parallel Tree Drafting","created":"2026-06-16","cited_by_count":15,"area":"inference"},{"id":"2607.04884","title":"HunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Better","created":"2026-07-06","cited_by_count":14,"area":"mllm"},{"id":"2602.23225","title":"Why Diffusion Language Models Struggle with Truly Parallel (Non-Autoregressive) Decoding?","created":"2026-02-26","cited_by_count":11,"area":"lr"},{"id":"2605.29343","title":"Draft-OPD: On-Policy Distillation for Speculative Draft Models","created":"2026-05-28","cited_by_count":11,"area":"inference"},{"id":"2604.06832","title":"Fast-dVLM: Efficient Block-Diffusion VLM via Direct Conversion from Autoregressive VLM","created":"2026-04-08","cited_by_count":9,"area":"mllm"},{"id":"2606.00487","title":"TAPS: Target-Aware Prefix Tree Selection for Diffusion-Drafted Speculative Decoding","created":"2026-05-30","cited_by_count":9,"area":"diffusion"},{"id":"2606.02091","title":"DFlare: Scaling Up Draft Capacity for Block Diffusion Speculative Decoding","created":"2026-06-01","cited_by_count":9,"area":"inference"},{"id":"2606.12370","title":"Breaking Entropy Bounds: Accelerating RL Training via MTP with Rejection Sampling","created":"2026-06-10","cited_by_count":9,"area":null},{"id":"2608.02365","title":"Faster-WAM: Do World Action Models Need Deep Action Modules?","created":"2026-08-03","cited_by_count":9,"area":"wm"},{"id":"2605.08632","title":"PARD-2: Target-Aligned Parallel Draft Model for Dual-Mode Speculative Decoding","created":"2026-05-09","cited_by_count":8,"area":"inference"},{"id":"2608.02438","title":"xPress: Parallel Refinement for Diffusion Drafters in Speculative Decoding","created":"2026-08-03","cited_by_count":8,"area":"inference"},{"id":"2605.20104","title":"Draft Less, Retrieve More: Hybrid Tree Construction for Speculative Decoding","created":"2026-05-19","cited_by_count":6,"area":"inference"},{"id":"2606.01774","title":"FLARE: Diffusion for Hybrid Language Model","created":"2026-06-01","cited_by_count":6,"area":null},{"id":"2606.01813","title":"Cost-Aware Diffusion Draft Trees for Speculative Decoding","created":"2026-06-01","cited_by_count":6,"area":"inference"},{"id":"2608.13524","title":"DARTree: Speculative Diffusion Decoding with Autoregressive Draft Trees","created":"2026-08-13","cited_by_count":6,"area":"inference"},{"id":"2604.26412","title":"When Hidden States Drift: Can KV Caches Rescue Long-Range Speculative Decoding?","created":"2026-04-29","cited_by_count":5,"area":"inference"},{"id":"2607.14647","title":"D-cut: Adaptive Verification Depth Pruning for Batched Speculative Decoding","created":"2026-07-16","cited_by_count":5,"area":"moe"},{"id":"2608.30135","title":"Verification-Aware Training for Speculative Decoding","created":"2026-08-31","cited_by_count":5,"area":"inference"},{"id":"2605.00342","title":"Making Every Verified Token Count: Adaptive Verification for MoE Speculative Decoding","created":"2026-05-01","cited_by_count":4,"area":"moe"},{"id":"2605.09992","title":"Attention Drift: What Autoregressive Speculative Decoding Models Learn","created":"2026-05-11","cited_by_count":4,"area":"inference"},{"id":"2605.12825","title":"Orthrus: Memory-Efficient Parallel Token Generation via Dual-View Diffusion","created":"2026-05-12","cited_by_count":4,"area":"diffusion"},{"id":"2606.03819","title":"TreeFlash: Parallel AR-Approximation for Faster Speculative Decoding","created":"2026-06-02","cited_by_count":4,"area":"inference"},{"id":"2607.07409","title":"DeLS-Spec: Decoupled Long-Short Contexts for Parallel Speculative Drafting","created":"2026-07-08","cited_by_count":4,"area":"inference"},{"id":"2607.25852","title":"AngelSpec: Towards Real-World High Performance Inference with Speculative Decoding","created":"2026-07-28","cited_by_count":4,"area":"inference"},{"id":"2608.20530","title":"LiLiCorr: Lightweight Likelihood Correlation of Parallel Drafts for Speculative Decoding","created":"2026-08-20","cited_by_count":4,"area":"inference"},{"id":"2605.09329","title":"Test-Time Speculation","created":"2026-05-10","cited_by_count":3,"area":"inference"},{"id":"2606.11552","title":"Teaching Diffusion to Speculate Left-to-Right","created":"2026-06-10","cited_by_count":3,"area":null},{"id":"2607.01893","title":"Spec-AUF: Accept-Until-Fail Training under Train-Inference Misalignment for Masked Block Drafters","created":"2026-07-02","cited_by_count":3,"area":"inference"},{"id":"2607.06763","title":"Trees from Marginals: Autoregressive drafting with factorized priors","created":"2026-07-07","cited_by_count":3,"area":"inference"},{"id":"2607.08690","title":"A Practical Investigation of Training-free Relaxed Speculative Decoding","created":"2026-07-09","cited_by_count":3,"area":"inference"},{"id":"2607.22634","title":"PRESTO: Prefix-Aligned Tree Drafting for Diffusion Speculative Decoding","created":"2026-06-20","cited_by_count":3,"area":"inference"},{"id":"2608.02123","title":"From Chains to Trees: Parent-Conditioned Drafting for Semi-Autoregressive Speculative Decoding","created":"2026-08-03","cited_by_count":3,"area":"inference"},{"id":"2609.02108","title":"Predict, Don't Iterate: Efficient Adaptive-Length Infilling for Diffusion Language Models","created":"2026-09-02","cited_by_count":3,"area":"diffusion"},{"id":"2609.07108","title":"Online Draft Co-Training for Speculative Decoding in Large-Scale, Long-Context RL Post-Training","created":"2026-09-07","cited_by_count":3,"area":"lr"},{"id":"2603.07475","title":"A Comparative analysis of Layer-wise Representational Capacity in AR and Diffusion LLMs","created":"2026-03-08","cited_by_count":2,"area":"diffusion"},{"id":"2605.07698","title":"Future Validity is the Missing Statistic: From Impossibility to $\\Phi$-Estimation for Grammar-Faithful Speculative Decoding","created":"2026-05-08","cited_by_count":2,"area":"inference"},{"id":"2605.20022","title":"FlexDraft: Flexible Speculative Decoding via Attention Tuning and Bonus-Guided Calibration","created":"2026-05-19","cited_by_count":2,"area":"inference"},{"id":"2605.29727","title":"Bastion: Budget-Aware Speculative Decoding with Tree-structured Block Diffusion Drafting","created":"2026-05-28","cited_by_count":2,"area":"inference"},{"id":"2606.02544","title":"SimSD: Simple Speculative Decoding in Diffusion Language Models","created":"2026-06-01","cited_by_count":2,"area":"diffusion"},{"id":"2606.04446","title":"D^2SD: Accelerating Speculative Decoding with Dual Diffusion Draft Models","created":"2026-06-03","cited_by_count":2,"area":"inference"},{"id":"2606.08357","title":"Forward-Free Diffusion Language Models with BPTT-Free Looped Refinement","created":"2026-06-06","cited_by_count":2,"area":"diffusion"},{"id":"2606.31315","title":"BlockPilot: Instance-Adaptive Policy Learning for Diffusion-based Speculative Decoding","created":"2026-06-30","cited_by_count":2,"area":"inference"},{"id":"2607.08642","title":"DominoTree: Conditional Tree-Structured Drafting with Domino for Speculative Decoding","created":"2026-07-09","cited_by_count":2,"area":"inference"},{"id":"2608.22788","title":"TailSieve: Partial-Rollout-Guided Tail Routing for LLM Rollouts","created":"2026-08-24","cited_by_count":2,"area":"distill"},{"id":"2608.29748","title":"ReTrace: Rejected-Trajectory Conditioning for Speculative Decoding","created":"2026-08-30","cited_by_count":2,"area":"inference"},{"id":"2609.04010","title":"Unlocking Lossless Speedups in LLMs via Discrete Diffusion","created":"2026-09-03","cited_by_count":2,"area":"diffusion"},{"id":"2609.06498","title":"DFlow: Enabling Verifier Information Flow in Block Diffusion Speculative Decoding","created":"2026-09-06","cited_by_count":2,"area":"inference"},{"id":"2609.17184","title":"LoopSpec: Pipelined Self-Speculative Decoding for Looped Transformers","created":"2026-09-15","cited_by_count":2,"area":"inference"},{"id":"2609.27396","title":"When Parallel Drafter Meets Parallel Speculative Decoding","created":"2026-09-23","cited_by_count":2,"area":"inference"},{"id":"2604.09731","title":"SMART: When is it Actually Worth Expanding a Speculative Tree?","created":"2026-04-09","cited_by_count":1,"area":"inference"},{"id":"2605.30852","title":"Speculative Pipeline Decoding: Higher-Accuracy Drafting with Hidden Latency via Pipeline Parallelism","created":"2026-05-29","cited_by_count":1,"area":"inference"},{"id":"2606.07710","title":"WhiFlash: Accelerating Speculative Decoding with Token-Level Cross-Paradigm Routing","created":"2026-06-05","cited_by_count":1,"area":"agents"},{"id":"2606.30265","title":"When Is a Draft Accepted? A Theory of Acceptance in Speculative Decoding","created":"2026-06-29","cited_by_count":1,"area":"inference"},{"id":"2608.00531","title":"CURE: Local Uncertainty Repair for Block-Parallel Speculative Decoding","created":"2026-08-01","cited_by_count":1,"area":"inference"},{"id":"2608.00814","title":"OoO-Spec: Out-of-Order Semantic Speculation for Fast Tool Calling","created":"2026-08-01","cited_by_count":1,"area":"agents"},{"id":"2608.02625","title":"Speculative Correction: Draft-then-Refine Decoding for Diffusion Language Models","created":"2026-07-21","cited_by_count":1,"area":"diffusion"},{"id":"2608.03457","title":"LLaDA MoE v2: Scaling Mixture-of-Experts Diffusion Language Models","created":"2026-08-04","cited_by_count":1,"area":"diffusion"},{"id":"2608.05448","title":"DBLAST: Dependent Block Drafting for Stochastic Speculative Decoding","created":"2026-08-05","cited_by_count":1,"area":"inference"},{"id":"2608.15763","title":"Training Agents to Evolve with Their Harness: TaoLive Digital Avatar Agent Technical Report","created":"2026-08-16","cited_by_count":1,"area":"agents"},{"id":"2608.15930","title":"UI-Mate: Advancing Open-Weight Foundation GUI Agents with In-Context Demonstrations","created":"2026-08-16","cited_by_count":1,"area":"agents"},{"id":"2608.27339","title":"Beyond Parallel Blindness: Information Floors and Model Gaps in Block Drafting","created":"2026-08-27","cited_by_count":1,"area":null},{"id":"2609.02897","title":"Margins, Not Windows: Training-Free Per-Step Lossy Speculative Decoding","created":"2026-07-03","cited_by_count":1,"area":"inference"},{"id":"2609.14717","title":"Carryover Drafting: Recycling Rejected States for Speculative Decoding","created":"2026-09-13","cited_by_count":1,"area":"inference"},{"id":"2609.22098","title":"TreeSpark: Calibrated, Load-Adaptive Draft Trees for Semi-Autoregressive Speculative Decoding","created":"2026-08-12","cited_by_count":1,"area":"inference"},{"id":"2609.24197","title":"H-Spec: Parallel Speculative Decoding Without a Drafter-Side KV Cache","created":"2026-09-21","cited_by_count":1,"area":"ssm"},{"id":"2609.26368","title":"HySparse2: Hybrid Sparse Attention with Two-Level KV Sharing","created":"2026-09-22","cited_by_count":1,"area":"inference"},{"id":"2609.36173","title":"Draft in Parallel, Condition Through Depth: Adjacent Causal Injection for Speculative Decoding","created":"2026-09-28","cited_by_count":1,"area":"inference"},{"id":"2610.11959","title":"MiMo-V2.6: Scaling Reinforcement Learning Towards Self-Improvement","created":"2026-10-08","cited_by_count":1,"area":"lr"},{"id":"2604.15672","title":"Faster LLM Inference via Sequential Monte Carlo","created":"2026-04-17","cited_by_count":0,"area":"inference"},{"id":"2606.13795","title":"DiPOD: Diffusion Policy Optimization without Drifting Apart","created":"2026-06-11","cited_by_count":0,"area":"diffusion"},{"id":"2606.15805","title":"Mean-Field Parallel Decoding for Discrete Diffusion Language Models","created":"2026-06-14","cited_by_count":0,"area":"diffusion"},{"id":"2606.26744","title":"HyperDFlash: Hyper-Connection-Aligned Block Speculative Decoding with Gated Residual Reduction","created":"2026-06-25","cited_by_count":0,"area":"inference"},{"id":"2607.04244","title":"Quantize the Target, Quantize the Drafter: Efficient Inference with Qwen3.5-4B","created":"2026-07-05","cited_by_count":0,"area":"inference"},{"id":"2607.05148","title":"Fully Rotation-Equivariant Spectral-Spatial Learning for Multispectral Object Detection","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2607.12422","title":"Accepted Prefixes Are Not All You Need: A Negative Result on PEFT-Based Block-Diffusion Drafting","created":"2026-07-14","cited_by_count":0,"area":"inference"},{"id":"2607.14735","title":"CoTu at EXACT 2026: Neuro-Symbolic Reasoning for Transparent Educational QA","created":"2026-07-16","cited_by_count":0,"area":"lr"},{"id":"2607.21535","title":"Windowed-MTP: Removing the Full-Context Draft-KV Tax at Million-Token Context","created":"2026-07-23","cited_by_count":0,"area":"inference"},{"id":"2608.03769","title":"MDLMPE: Distribution Aware Positional Encoding for Masked Diffusion Language Models","created":"2026-08-04","cited_by_count":0,"area":"diffusion"},{"id":"2608.04505","title":"K-EXAONE 2.0 Technical Report","created":"2026-08-05","cited_by_count":0,"area":"moe"},{"id":"2608.12932","title":"FlashDrive: Flash Vision-Language-Action Inference for Autonomous Driving","created":"2026-08-13","cited_by_count":0,"area":"vla"},{"id":"2608.14787","title":"From Positionwise Confidence to Prefix Scheduling: Verifier Skipping in Speculative Decoding","created":"2026-08-14","cited_by_count":0,"area":"inference"},{"id":"2608.20743","title":"Is Multimodal Speculative Decoding Ready for Diffusion-Based Parallel Drafting? A Survey and Empirical Diagnosis","created":"2026-08-21","cited_by_count":0,"area":"inference"},{"id":"2608.22883","title":"FOVEA: Focused On-Demand Visual Evidence Adaptation for Cache-Friendly Multimodal Speculative Decoding","created":"2026-08-24","cited_by_count":0,"area":"mllm"},{"id":"2608.30427","title":"Ceiling-Clipped Acceptance Histograms Indicate Stranded Speed-up in Block-Diffusion Speculative Decoding","created":"2026-08-31","cited_by_count":0,"area":"inference"},{"id":"2609.00355","title":"Vision Is Not Overhead: One-Pass Block Drafting for Lossless Speculative Decoding in Vision-Language Models","created":"2026-08-31","cited_by_count":0,"area":"mllm"},{"id":"2609.03181","title":"Jina-OCR-v1: Efficient Document Parsing with Speculative Decoding and Dense Verifiable Rewards","created":"2026-09-02","cited_by_count":0,"area":"inference"},{"id":"2609.09338","title":"Osprey: Target-agnostic Pre-training Makes Stronger Drafters in Speculative Decoding","created":"2026-09-08","cited_by_count":0,"area":"inference"},{"id":"2609.10715","title":"NCP-ArchPreview Technical Report: Moving towards Latent Space Language Models through Next Concept Prediction","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.15296","title":"Reason What Matters: Retrieval-Grounded Reasoning for Universal Multimodal Embeddings","created":"2026-09-14","cited_by_count":0,"area":"lr"},{"id":"2609.19242","title":"Block Parallelism For Efficient Distributed Long-Context Diffusion Language Model Training","created":"2026-09-16","cited_by_count":0,"area":"diffusion"},{"id":"2609.23900","title":"LumoTree: Path-Parallel Speculative Verification for Hybrid Language Models","created":"2026-09-20","cited_by_count":0,"area":"inference"},{"id":"2609.26638","title":"Diffusion Drafts, AR Verifies: Accelerating Document OCR with Self-Speculative Decoding","created":"2026-09-22","cited_by_count":0,"area":"inference"},{"id":"2609.30474","title":"Mentored Decoding: Faster Inference meets Boosting","created":"2026-09-24","cited_by_count":0,"area":"inference"},{"id":"2609.33245","title":"Acoustic Progress Propagation for Long-Horizon Speculative Decoding in ASR","created":"2026-09-27","cited_by_count":0,"area":"inference"},{"id":"2609.33385","title":"OLED-MoE: Accelerating MoE-Based dLLM Inference via Inter-Iteration Locality-Aware Expert Offloading","created":"2026-09-27","cited_by_count":0,"area":"moe"}],"next_cursor":"100"}