Papersby GlyphLongCodeZip: Compress Long Context for Code Language Models research paper by Stanford University, 2025
Stanford University · Inference and efficiency · Oct 1, 2025 · 54 citations · 77 upvotes · unverified
What it shows
LongCodeZip is a code compression framework for LLMs that uses dual-stage compression to reduce context size without degrading performance, improving efficiency in code intelligence applications.
By Yuling Shi, Yichun Qian, Hongyu Zhang and 2 more · arXiv 2510.00446 · PDF · Code
UnverifiedHugging Face's summary; not yet checked by hand.
More from Stanford University
All 12Hybrid Reasoning AgentsThis paper introduces an agent architecture that dynamically switches between latent reasoning and text-based interaction to improve performance and inference speed.
Stanford University41 upvotesRead →Thinking Inertia: LLMs Keep Thinking When Told Not ToThis paper shows that explicit controls often fail to stop LLMs from generating internal reasoning traces, a phenomenon the authors call thinking inertia.Stanford University244 upvotesRead →Stateless Language Agents: Scaling Long-Horizon Automated ResearchThis paper introduces a framework where agents remain stateless, allowing a central harness to manage research state and improve long-horizon task efficiency.Stanford University1 citations30 upvotesRead →FAMOS: Feed-Forward 3D Articulation Modeling from Sparse ObservationsFAMOS is a feed-forward model that predicts articulated object motion from sparse point cloud observations.Stanford University40 upvotesRead →AISPA: User-Centric System Prompt Auditing for Large Language Model ApplicationsAISPA is a framework for auditing system prompts in commercial AI products to ensure they are protective of users.Stanford University36 upvotesRead →Recursive Multi-Agent SystemsRecursiveMAS extends recursive scaling principles from single models to multi-agent systems, enabling collaborative reasoning through iterative latent-space computations with improved efficiency and accuracy.Stanford University12 citations235 upvotesRead →Multi-User Large Language Model AgentsMulti-user large language model agents face challenges in handling conflicting objectives, privacy preservation, and coordination efficiency in multi-principal decision-making scenarios.Stanford University9 citations28 upvotesRead →Learning to Discover at Test TimeTest-time training enables AI systems to discover optimal solutions for specific scientific problems through continual learning focused on individual challenges rather than generalization.Stanford University118 citations45 upvotesRead →
Other inference and efficiency papers
TopicEfficient 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 →Group Sequence Policy OptimizationGroup Sequence Policy Optimization (GSPO) is a reinforcement learning algorithm that improves training efficiency and performance of large language models by using sequence-level importance ratios and operations.
Alibaba (Qwen)814 citations323 upvotesRead →Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse AttentionNSA, a trainable sparse attention mechanism, enhances long-context modeling efficiency without sacrificing performance, achieving improvements in speed and accuracy over full attention models.
DeepSeek596 citations157 upvotesRead →SmolVLM: Redefining small and efficient multimodal modelsSmolVLM, a series of compact multimodal models, achieves high performance with minimal GPU memory usage, making efficient deployment on mobile and edge devices possible.
Hugging Face330 citations212 upvotesRead →Chronos-2: From Univariate to Universal ForecastingChronos-2, a pretrained model with a group attention mechanism, achieves state-of-the-art performance in zero-shot univariate, multivariate, and covariate-informed forecasting tasks.
Amazon276 citations28 upvotesRead →Inference-Time Scaling for Generalist Reward ModelingSelf-Principled Critique Tuning enhances pointwise generative reward modeling for large language models, improving scalability and quality compared to existing methods.DeepSeek259 citations59 upvotesRead →
Amazon276 citations28 upvotesRead →Inference-Time Scaling for Generalist Reward ModelingSelf-Principled Critique Tuning enhances pointwise generative reward modeling for large language models, improving scalability and quality compared to existing methods.About this paper
- Venue
- International Conference on Automated Software Engineering
- Citations
- 54, 9 influential · Semantic Scholar
- Upvotes
- 77 · Hugging Face
- Lab
- Stanford University
Changes
Influential citations rose from 8 to 9.
Citations rose from 49 to 54.
Citations rose from 48 to 49.
Influential citations rose from 7 to 8.
Citations rose from 47 to 48.
A first count of 7 influential citations.
A first count of 47 citations.
Found by the weekly Hugging Face scan; not yet checked by hand.