Papersby GlyphUC Berkeley research papers
A university publishing mostly on inference and efficiency, best known here for Efficient Memory Management for Large Language Model Serving with PagedAttention.14 papers · 10,260 citations · latest Oct 2026
Correction Training for Diffusion ModelsThis method adds a correction step to diffusion models to fix errors that accumulate during the image generation process.
UC Berkeley42 upvotesRead →OmniTaskonomy: When Does Visual Generation Improve Visual Understanding?This paper maps how visual generation tasks improve visual understanding capabilities, revealing specific task-dependent transfer benefits.UC Berkeley57 upvotesRead →FreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive ExecutionFreeToken is an edge-native Mixture-of-Experts serving system that dynamically maps computation and model state onto heterogeneous local hardware to run large open-weight models on personal machines.UC Berkeley8 citations86 upvotesRead →Playful Agentic Robot LearningEmbodied robots learn reusable skills through self-directed play and exploration, then apply these skills to improve performance on downstream tasks without additional training.UC Berkeley37 citations49 upvotesRead →Agents' Last ExamOver 1,000 real, checkable professional tasks written with 250+ industry experts; the hardest tier is far from solved.UC Berkeley42 citations393 upvotesRead →Flash-KMeans: Fast and Memory-Efficient Exact K-MeansFlash-kmeans enables efficient online k-means clustering on GPUs through novel kernel-level optimizations that eliminate I/O bottlenecks and reduce atomic write contention.UC Berkeley16 citations64 upvotesRead →dLLM: Simple Diffusion Language ModelingA unified open-source framework is presented that standardizes core components of diffusion language modeling for reproduction, customization, and accessible development of both large and small models.UC Berkeley18 citations136 upvotesRead →SLA2: Sparse-Linear Attention with Learnable Routing and QATSLA2 improves sparse-linear attention in diffusion models by introducing a learnable router, direct attention formulation, and quantization-aware fine-tuning for enhanced efficiency and quality.UC Berkeley1 citations59 upvotesRead →Quant VideoGen: Auto-Regressive Long Video Generation via 2-Bit KV-Cache QuantizationQuant VideoGen addresses KV cache memory limitations in autoregressive video diffusion models through semantic-aware smoothing and progressive residual quantization, achieving significant memory reduction with minimal latency impact.UC Berkeley29 citations35 upvotesRead →Residual Context Diffusion Language ModelsResidual Context Diffusion (RCD) enhances diffusion large language models by recycling discarded token information through contextual residuals, improving accuracy with minimal computational overhead.UC Berkeley13 citations36 upvotesRead →Latent Implicit Visual ReasoningThis paper introduces a task-agnostic mechanism for models to discover and use visual reasoning tokens without explicit supervision.UC Berkeley19 citations60 upvotesRead →TurboDiffusion: Accelerating Video Diffusion Models by 100-200 TimesTurboDiffusion accelerates video generation by 100-200x using attention acceleration, step distillation, and quantization, while maintaining video quality.UC Berkeley37 citations95 upvotesRead →Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with Continuous Visual TokensChain-of-Visual-Thought (COVT) enables Vision-Language Models to reason through visual tokens, improving their performance on perceptual tasks by capturing dense visual information.UC Berkeley75 citations29 upvotesRead →Efficient Memory Management for Large Language Model Serving with PagedAttentionvLLM manages the KV cache like pages of virtual memory, serving models with 2 to 4 times the throughput.UC Berkeley9,965 citations72 upvotesRead →
About and links
Topics: Inference and efficiency 5, Multimodal and robotics 2, Agents and evaluation 2, Reasoning 2, Architectures 1, Foundation models 1, Training and scaling 1
UC Berkeley lab profile on Labs (labs.fru.dev): leaders, models, landmarksNot in the companies.fru.dev registry yet; its papers are listed at /api/companies for the registry's nightly sync.