Ruby Finds Unsafe Rust Regions in Stripped Binaries
Instruction-level binary features train a classifier that recovers 91.75% of unsafe regions at a 6.16% false positive rate.
Jul 13, 20264 min2211.00111
Machine Learning
cs.LGAll aspects of machine learning research including supervised, unsupervised, and reinforcement learning.
Sort:
Full-Stack FP4 Narrows Pretraining Loss Gap
Module-specific NVFP4 quantization covers projections, optimizers, and attention, reaching a 1.47% loss gap on 3B/64B-token pretraining.
Jul 12, 20264 min2607.04422
Attention Alone Improves Machine Translation and Training Efficiency
The Transformer replaces recurrence and convolution with multi-head self-attention, reaching 28.4 BLEU on WMT 2014 English-German with shorter training.
Jul 12, 20264 min1706.03762 Code available
On-Policy Distillation Reduces Cross-Platform GUI Forgetting
Platform-conditioned teacher selection distills desktop and mobile policies into one continual learner, reaching 38.2% OSWorld and 12.0% MobileWorld success.
Jul 12, 20264 min2607.04425
Computer SciencePick
Neuro-Symbolic Reasoning Improves LLM Accuracy by 12-18%
Generating natural language explanations then verifying them symbolically outperforms chain-of-thought prompting.
Aug 5, 202410 min2408.01234 Code available
Self-Supervised Depth Estimation Gets Geometric Verification
Explicit multi-view geometry constraints improve monocular depth without any ground-truth supervision.
Jun 11, 20248 min2406.05678 Code available
Derivative-Free Optimization Scales to 10,000 Dimensions
Random subspace methods achieve convergence rates dependent on intrinsic dimensionality, not ambient dimension.
May 6, 202410 min2405.02345
Algorithm Unrolling Gets a Unified Convergence Theory
A framework bridges classical optimization and deep learning with provable guarantees for learned optimizers.
Mar 7, 202411 min2403.03210 Code available
Sparse Window Attention Extends Context to 128K Tokens
A hierarchical sparse decomposition achieves sub-quadratic long-range attention with minimal quality loss.
Feb 15, 20247 min2402.08901 Code available
Computer SciencePick
Constitutional AI Reduces Reliance on Human Safety Oversight
AI-generated feedback guided by explicit principles cuts the need for human reviewers in safety fine-tuning.
Jan 18, 202410 min2401.12345