{"total":55,"rows":[{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"id":"2601.20552","title":"DeepSeek-OCR 2: Visual Causal Flow","created":"2026-01-28","cited_by_count":74,"area":null},{"id":"2508.10711","title":"NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale","created":"2025-08-14","cited_by_count":57,"area":"diffusion"},{"id":"2601.06521","title":"BabyVision: Visual Reasoning Beyond Language","created":"2026-01-10","cited_by_count":49,"area":"lr"},{"id":"2511.15848","title":"Step-Audio-R1 Technical Report","created":"2025-11-19","cited_by_count":36,"area":"lr"},{"id":"2510.14648","title":"In-Context Learning with Unpaired Clips for Instruction-based Video Editing","created":"2025-10-16","cited_by_count":35,"area":null},{"id":"2601.09668","title":"STEP3-VL-10B Technical Report","created":"2026-01-14","cited_by_count":32,"area":null},{"id":"2510.10991","title":"A Survey on Agentic Multimodal Large Language Models","created":"2025-10-13","cited_by_count":23,"area":"mllm"},{"id":"2603.01050","title":"MM-DeepResearch: A Simple and Effective Multimodal Agentic Search Baseline","created":"2026-03-01","cited_by_count":20,"area":"agents"},{"id":"2512.22560","title":"RollArt: Disaggregated Multi-Task Agentic RL Training at Scale","created":"2025-12-27","cited_by_count":14,"area":"agents"},{"id":"2509.17863","title":"Expert-as-a-Service: Towards Efficient, Scalable, and Robust Large-scale MoE Serving","created":"2025-09-22","cited_by_count":13,"area":"moe"},{"id":"2601.20205","title":"Hyperparameter Transfer with Mixture-of-Expert Layers","created":"2026-01-28","cited_by_count":13,"area":"moe"},{"id":"2602.03916","title":"SpatiaLab: Can Vision-Language Models Perform Spatial Reasoning in the Wild?","created":"2026-02-03","cited_by_count":11,"area":"lr"},{"id":"2509.25160","title":"GSM8K-V: Can Vision Language Models Solve Grade School Math Word Problems in Visual Contexts","created":"2025-09-29","cited_by_count":8,"area":"lr"},{"id":"2512.13525","title":"Janus: Disaggregating Attention and Experts for Scalable MoE Inference","created":"2025-12-15","cited_by_count":8,"area":"moe"},{"id":"2602.06502","title":"DualMap: Enabling Both Cache Affinity and Load Balancing for Distributed LLM Serving","created":"2026-02-06","cited_by_count":8,"area":"inference"},{"id":"2512.03870","title":"Reconstructing KV Caches with Cross-layer Fusion For Enhanced Transformers","created":"2025-12-03","cited_by_count":6,"area":"inference"},{"id":"2602.00509","title":"PROBE: Co-Balancing Computation and Communication in MoE Inference via Real-Time Predictive Prefetching","created":"2026-01-31","cited_by_count":4,"area":"moe"},{"id":"2602.09721","title":"Revealing the Challenges of Attention-FFN Disaggregation for Modern MoE Models and Hardware Systems","created":"2026-02-10","cited_by_count":4,"area":"moe"},{"id":"2510.14686","title":"xLLM Technical Report","created":"2025-10-16","cited_by_count":3,"area":"inference"},{"id":"2509.26534","title":"Rearchitecting Datacenter Lifecycle for AI: A TCO-Driven Framework","created":"2025-09-30","cited_by_count":2,"area":null},{"id":"2511.23476","title":"Thinking by Doing: Building Efficient World Model Reasoning in LLMs via Multi-turn Interaction","created":"2025-11-28","cited_by_count":2,"area":"wm"},{"id":"2512.22492","title":"Role-Based Fault Tolerance System for LLM RL Post-Training","created":"2025-12-27","cited_by_count":2,"area":null},{"id":"2601.01310","title":"Making MoE-based LLM Inference Resilient with Tarragon","created":"2026-01-04","cited_by_count":2,"area":"moe"},{"id":"2601.21351","title":"Analytical Provisioning for Attention-FFN Disaggregated LLM Serving under Stochastic Workloads","created":"2026-01-29","cited_by_count":2,"area":"inference"},{"id":"2604.23996","title":"SMoES: Soft Modality-Guided Expert Specialization in MoE-VLMs","created":"2026-04-27","cited_by_count":2,"area":"mllm"},{"id":"2606.10493","title":"Achieving Cloud-Grade SLOs for Local Mixture-of-Experts Inference through CPU-GPU Hybrid Design","created":"2026-06-09","cited_by_count":2,"area":"moe"},{"id":"2508.03760","title":"FlashCommunication V2: Bit Splitting and Spike Reserving for Any Bit Communication","created":"2025-08-04","cited_by_count":1,"area":null},{"id":"2508.16151","title":"Hardwired-Neurons Language Processing Units as General-Purpose Cognitive Substrates","created":"2025-08-22","cited_by_count":1,"area":null},{"id":"2511.21431","title":"MemFine: Memory-Aware Fine-Grained Scheduling for MoE Training","created":"2025-11-26","cited_by_count":1,"area":"moe"},{"id":"2512.21487","title":"Efficient MoE Inference with Fine-Grained Scheduling of Disaggregated Expert Parallelism","created":"2025-12-25","cited_by_count":1,"area":"moe"},{"id":"2602.13033","title":"Buy versus Build an LLM: A Decision Framework for Governments","created":"2026-02-13","cited_by_count":1,"area":null},{"id":"2603.10353","title":"S-HPLB: Efficient LLM Attention Serving via Sparsity-Aware Head Parallelism Load Balance","created":"2026-03-11","cited_by_count":1,"area":"inference"},{"id":"2604.24441","title":"AutoGUI-v2: A Comprehensive Multi-Modal GUI Functionality Understanding Benchmark","created":"2026-04-27","cited_by_count":1,"area":null},{"id":"2606.24506","title":"CrossPool: Efficient Multi-LLM Serving for Cold MoE Models through KV-Cache and Weight Disaggregation","created":"2026-06-23","cited_by_count":1,"area":"moe"},{"id":"2607.18002","title":"ExpertPlex: A High-Goodput Disaggregated Serving System for MoE LLMs with Adaptive Persistent Kernels","created":"2026-07-20","cited_by_count":1,"area":"moe"},{"id":"2511.02248","title":"From Models to Operators: Rethinking Autoscaling Granularity for Large Generative Models","created":"2025-11-04","cited_by_count":0,"area":"lr"},{"id":"2512.23020","title":"OpenGround: Planning-based Online Perception for Open-World 3D Visual Grounding","created":"2025-12-28","cited_by_count":0,"area":null},{"id":"2603.06687","title":"TimeSpot: Benchmarking Geo-Temporal Understanding in Vision-Language Models in Real-World Settings","created":"2026-03-04","cited_by_count":0,"area":"wm"},{"id":"2603.13364","title":"FineRMoE: Dimension Expansion for Finer-Grained Expert with Its Upcycling Approach","created":"2026-03-09","cited_by_count":0,"area":"moe"},{"id":"2604.01181","title":"True (VIS) Lies: Analyzing How Generative AI Recognizes Intentionality, Rhetoric, and Misleadingness in Visualization Lies","created":"2026-04-01","cited_by_count":0,"area":"mllm"},{"id":"2604.10180","title":"Tessera: Unlocking Heterogeneous GPUs through Kernel-Granularity Disaggregation","created":"2026-04-11","cited_by_count":0,"area":null},{"id":"2604.26103","title":"AMMA: A Multi-Chiplet Memory-Centric Architecture for Low-Latency 1M Context Attention Serving","created":"2026-04-28","cited_by_count":0,"area":"inference"},{"id":"2605.11005","title":"DisagMoE: Computation-Communication overlapped MoE Training via Disaggregated AF-Pipe Parallelism","created":"2026-05-10","cited_by_count":0,"area":"moe"},{"id":"2605.21100","title":"NanoCP: Request-Level Dynamic Context Parallelism for Data-Expert Parallel Decoding","created":"2026-05-20","cited_by_count":0,"area":"moe"},{"id":"2605.28229","title":"VidPrism: Heterogeneous Mixture of Experts for Image-to-Video Transfer","created":"2026-05-27","cited_by_count":0,"area":"mllm"},{"id":"2606.22541","title":"ASAP: A Disaggregated and Asynchronous Inference System for MoE Prefill","created":"2026-06-21","cited_by_count":0,"area":"moe"},{"id":"2607.00151","title":"SmoothAgent: Efficient Long-Horizon LLM-Based Agent Serving with Lookahead Context Engineering","created":"2026-06-30","cited_by_count":0,"area":"inference"},{"id":"2607.05876","title":"Think Before You Grid-Search: Floor-First Triage for LLM Serving","created":"2026-07-07","cited_by_count":0,"area":"inference"},{"id":"2608.07964","title":"EasyBalance: Cross-Layer Load Balancing in Distributed MoE Inference","created":"2026-08-08","cited_by_count":0,"area":"moe"},{"id":"2608.13499","title":"OpScale: Operator-level Provisioning and Autoscaling for LLM Serving","created":"2026-08-13","cited_by_count":0,"area":"inference"},{"id":"2608.15473","title":"Q-First: Most of Attention Needs Only the Query in Disaggregated LLM Decoding","created":"2026-08-16","cited_by_count":0,"area":"inference"},{"id":"2609.08755","title":"Kairos: A Dataset for Fine-Grained Video-Language Modeling over Space, Time, and Dynamics","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.13134","title":"Rethinking Heterogeneous System Disaggregation for Subquadratic Attention","created":"2026-09-11","cited_by_count":0,"area":"lr"},{"id":"2609.32780","title":"OmniMoE-VL: A Sparse Vision-Language Model with Coupled Visual-Depth Routing","created":"2026-09-26","cited_by_count":0,"area":"mllm"}],"next_cursor":null}