arXiv AI
Jul 7
Rethinking Neural Nonlinearity as Gating
arXiv:2607. 03148v1 Announce Type: cross Abstract: Activation functions are considered an essential primitive for neural nonlinearity, i.
Inference efficiency
Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv Machine Learning
Jul 7
Efficient Cross-Validation for Sparse Linear Regression
arXiv:2306. 14851v5 Announce Type: replace-cross Abstract: Given a high-dimensional covariate matrix and a response vector, ridge-regularized sparse linear regression selects a subset of features that explains the relationship between covariates and the response in an interpretable manner.
arXiv AI
Jul 7
Do All Visual Tokens Matter Equally? Object-Evidence Preserving Token Merging for Vision-Language Retrieval
arXiv:2607. 04605v1 Announce Type: cross Abstract: Multi-vector vision-language retrieval preserves fine-grained visual evidence through maximum-similarity late interaction, but dense image-side tokens make storage and scoring expensive.
arXiv AI
Jul 7
Causal Mechanism Reduction: Mechanism Replacement for Neural Network Pruning and Abstraction
arXiv:2602. 24266v2 Announce Type: replace-cross Abstract: Which internal mechanisms of a neural network can be replaced while preserving the computation it performs?
arXiv AI
Jul 7
Large Language Models Generate Harmful Responses Using a Distinct Mechanism, Shared Across Harm Types
arXiv:2604. 09544v2 Announce Type: replace-cross Abstract: Large language models (LLMs) undergo alignment training to avoid harmful behaviors, yet the resulting safeguards remain brittle: jailbreaks routinely bypass them, and fine-tuning on narrow domains can induce ``emergent misalignment'' that generalizes broadly.
arXiv Machine Learning
Jul 7
Uni-OPD: Unifying On-Policy Distillation with a Dual-Perspective Recipe
arXiv:2605. 03677v2 Announce Type: replace Abstract: On-policy distillation (OPD) has recently emerged as an effective post-training paradigm for consolidating the capabilities of specialized expert models into a single student model.
arXiv AI
Jul 7
KARA: Efficient Reasoning LLM Serving via Sliding-Window KV Cache Compression
arXiv:2607. 01237v2 Announce Type: replace-cross Abstract: Reasoning language models often generate long chain-of-thought (CoT), which accumulates a massive KV cache during the decoding phase and incurs high decoding latency and limited throughput.
arXiv AI
Jul 7
Harmonic-Aware Transformer for Real-Time Catheter Localization in Interventional Procedures of Magnetic Particle Imaging
arXiv:2607. 02919v1 Announce Type: cross Abstract: Magnetic particle imaging (MPI) enables real-time, radiation-free tracking of magnetic nanoparticle-coated instruments, making it highly suitable for interventional procedures.
arXiv AI
Jul 7
Formal Disco: Scalable Open-Ended Generation of Formally Verified Programs
arXiv:2607. 04631v1 Announce Type: new Abstract: The cost of producing code is rapidly diminishing with increasingly capable AI agents, while quality assurance of generated programs has not kept pace.
arXiv Machine Learning
Jul 7
Few-Step Diffusion Language Models via Trajectory Self-Distillation
arXiv:2602. 12262v4 Announce Type: replace-cross Abstract: Diffusion large language models (DLLMs) have emerged as powerful generative models with the promise of fast text generation through parallel decoding.
arXiv Machine Learning
Jul 7
Non-Convex Sparse Reinforcement Learning via Non-Monotone Inclusions
arXiv:2607. 04990v1 Announce Type: new Abstract: This work delivers two key contributions: one to efficient feature selection in reinforcement learning (RL), the other to the theory of non-monotone inclusions.
arXiv Machine Learning
Jul 7
SAD-LoRA: Spectral Alignment for Low-Rank Knowledge Distillation
arXiv:2607. 04306v1 Announce Type: new Abstract: Distilling a fine-tuned teacher into a LoRA-adapted student is a standard recipe for parameter-efficient compression, but output-level KD does not explicitly control which rank-$r$ weight subspace the adapter occupies.
arXiv AI
Jul 7
Walrus: A Cross-Domain Foundation Model for Continuum Dynamics
arXiv:2511. 15684v2 Announce Type: replace-cross Abstract: Foundation models have transformed machine learning for language and vision, but achieving comparable impact in physical simulation remains a challenge.
arXiv AI
Jul 7
Prima.cpp: Fast 30-70B LLM Inference on Heterogeneous and Low-Resource Home Clusters
arXiv:2504. 08791v3 Announce Type: replace-cross Abstract: On-device inference offers privacy, offline use, and instant response, but consumer hardware restricts large language models (LLMs) to low throughput and capability.
arXiv Machine Learning
Jul 7
A Unified Framework for Quantized and Continuous Strong Lottery Tickets
arXiv:2607. 03860v1 Announce Type: new Abstract: The Strong Lottery Ticket Hypothesis (SLTH) asserts that sufficiently overparameterized, randomly initialized neural networks contain sparse subnetworks that, even without any training, can match the performance of a small trained network on a given dataset.
arXiv AI
Jul 7
From Arithmetic to Logic: The Resilience of Logic and Lookup-Based Neural Networks Under Parameter Bit-Flips
arXiv:2603. 22770v2 Announce Type: replace-cross Abstract: The deployment of deep neural networks (DNNs) in safety-critical edge environments necessitates robustness against hardware-induced bit-flip errors.
arXiv AI
Jul 7
Automating the Design of Embodied Agent Architectures
arXiv:2606. 30111v2 Announce Type: replace-cross Abstract: Embodied agents are typically built as hand-designed compositions of perception, memory, planning, and action modules.
arXiv AI
Jul 7
Shao: Scaling Acoustic Token Language Models Toward High-Fidelity Music Generation
arXiv:2605. 01790v2 Announce Type: replace-cross Abstract: A common design pattern in high-quality music generation is to handle structure and fidelity in different representation spaces: a generator first models high-level structure, followed by diffusion-based or neural decoding stages that reconstruct fine details.
arXiv AI
Jul 7
Fusion: A Framework for Unified Sequential Token AdaptatIon in VisiOn TraNsformers
arXiv:2607. 02612v1 Announce Type: cross Abstract: Vision Transformers achieve strong image classification accuracy but process all image regions with nearly the same computation, even when many regions are redundant or uninformative.
arXiv Machine Learning
Jul 7
PLoRA: Efficient Concurrent LoRA Training for Large Language Models
arXiv:2508. 02932v2 Announce Type: replace Abstract: Low-Rank Adaptation (LoRA) has gained popularity as a fine-tuning approach for Large Language Models (LLMs) due to its low resource requirements and good performance.