HeatKV doubles KV-cache compression ratios over prior methods for VAR models by creating static head-specific pruning schedules from attention rankings on a calibration set, while preserving image quality on Infinity-2B.
Qwen3 technical report
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
Real developer IDE traces differ substantially from LLM simulations in behavior and structure; current proactive assistants are unreliable on real traces, and simulated data cannot substitute for real data in training.
Reasoning-tuned LLMs align with human comprehension failure patterns under code obfuscation using the Block Model, unlike instruction-tuned variants.
citing papers explorer
-
HeatKV: Head-tuned KV-cache Compression for Visual Autoregressive Modeling
HeatKV doubles KV-cache compression ratios over prior methods for VAR models by creating static head-specific pruning schedules from attention rankings on a calibration set, while preserving image quality on Infinity-2B.
-
An Empirical Study of Proactive Coding Assistants in Real-World Software Development
Real developer IDE traces differ substantially from LLM simulations in behavior and structure; current proactive assistants are unreliable on real traces, and simulated data cannot substitute for real data in training.
-
Do Machines Struggle Where Humans Do? LLM and Human Comprehension of Obfuscated Code
Reasoning-tuned LLMs align with human comprehension failure patterns under code obfuscation using the Block Model, unlike instruction-tuned variants.