arXiv AI
Jun 9
High-Rate Quantized Matrix Multiplication II
arXiv:2605. 13768v2 Announce Type: replace-cross Abstract: This is the second part of the work investigating quantized matrix multiplication (MatMul).
Inference efficiency
Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv AI
Jun 9
LEAP: Learnable End-to-End Adaptive Pruning of Large Language Models
arXiv:2605. 17289v2 Announce Type: replace-cross Abstract: Unstructured sparsity is now natively accelerated by recent GPU kernels and dataflow hardware, shifting the bottleneck from inference execution to the pruning algorithm.
arXiv AI
Jun 9
A Comparative Study of Student Perspectives on Technical Writing Feedback Quality: Evaluating LLMs, SLMs, and Humans in Computer Science Topics
arXiv:2601. 11541v2 Announce Type: replace-cross Abstract: To address the scalability of feedback in computer science while mitigating the privacy and cost limitations of commercial Large Language Models (LLMs), this study evaluates a locally hosted Small Language Model (SLM).
arXiv Machine Learning
Jun 9
SNN-MLIR: An MLIR Dialect for Compiling Neuromorphic SNNs from NIR to Bare-Metal C
arXiv:2606. 09213v1 Announce Type: cross Abstract: Spiking neural networks (SNNs) are increasingly trained in a wide range of frameworks (SnnTorch, Lava, Norse, and others) each with its own model format.
arXiv Machine Learning
Jun 9
Distilling Safe LLM Systems via Soft Prompts for On Device Settings
arXiv:2606. 09388v1 Announce Type: new Abstract: Deploying safe large language models (LLMs) on resource-constrained edge devices presents a critical challenge: while dual-model systems combining LLMs with guard models provide effective safety guarantees, their substantial memory and computational demands make them prohibitively expensive for on-device deployment.
arXiv Machine Learning
Jun 9
Characterizing the Impact of NVFP4 Quantization for Low-Power Edge AI Deployment
arXiv:2606. 06527v2 Announce Type: replace-cross Abstract: Energy-efficient neural-network inference at the edge requires reducing arithmetic cost, memory traffic, computation energy, and storage overhead while maintaining acceptable accuracy.
arXiv Machine Learning
Jun 9
Few-step Cofolding with All-Atom Flow Maps
arXiv:2606. 08375v1 Announce Type: new Abstract: All-atom generative modeling of 3D biomolecular complexes has emerged as the dominant paradigm for predicting the structure of proteins and protein-ligand systems.
arXiv AI
Jun 9
Stage-1 Controls the Entropy Regime, Not the Outcome
arXiv:2606. 09059v1 Announce Type: cross Abstract: Two-stage post-training -- a Stage-1 warm-start (supervised fine-tuning, SFT, or on-policy distillation, OPD) followed by Stage-2 reinforcement learning (RL) -- is increasingly used for vision-language models (VLMs).
arXiv AI
Jun 9
Decoupling Semantics and Logic: A Training-Free Coarse-to-Fine Pipeline for Video Retrieval-Augmented Generation
arXiv:2606. 07924v1 Announce Type: cross Abstract: This paper presents our system description for the 2nd Workshop on Multimodal Augmented Generation via MultimodAl Retrieval (MAGMaR).
arXiv AI
Jun 9
AliyunConsoleAgent: Training Web Agents in Real-World Cloud Environments via Distillation and Reinforcement Learning
arXiv:2606. 09447v1 Announce Type: new Abstract: We present AliyunConsoleAgent, a web agent framework for automated documentation verification in real-world cloud consoles.
arXiv AI
Jun 9
ConMem: Structured Memory-Guided Adaptation in Training-Free Multi-Agent Systems
arXiv:2606. 08702v1 Announce Type: new Abstract: Recent advances have improved the adaptive capabilities of LLM-based multi-agent systems (MAS) through memory-, skill-, and learning-based approaches, yet these approaches remain challenged by noisy trajectories, insufficient modeling of memory-skill relations, and reliance on additional training or high-quality supervision.
arXiv AI
Jun 9
A Geometric Unification of Concept Learning with Concept Cones
arXiv:2512. 07355v2 Announce Type: replace Abstract: Two traditions of interpretability have evolved side by side but seldom spoken to each other: Concept Bottleneck Models (CBMs), which prescribe what a concept should be, and Sparse Autoencoders (SAEs), which discover what concepts emerge.
arXiv AI
Jun 9
DiffoR: A Unified Continuous Generative Framework for Universal Ordinal Regression
arXiv:2606. 07599v1 Announce Type: cross Abstract: Ordinal Regression (OR) aims to predict target values with inherent order, underpinning critical applications across diverse domains, from recommender systems to computer vision.
arXiv AI
Jun 9
Hyperflux: Pruning Reveals Importance
arXiv:2504. 05349v4 Announce Type: replace-cross Abstract: Network pruning is used to reduce inference latency and power consumption in large neural networks.
arXiv Machine Learning
Jun 9
Escaping the KL Agreement Trap in On-Policy Distillation
arXiv:2606. 09471v1 Announce Type: new Abstract: On-policy distillation (OPD) provides dense token-level supervision by asking a teacher to score student-generated rollouts.
arXiv AI
Jun 9
Structure-Conditioned Actor-Critic Branches for Quality-Diversity Reinforcement Learning
arXiv:2606. 08735v1 Announce Type: new Abstract: Quality-diversity reinforcement learning (QD-RL) aims to construct policy repertoires that contain both high-performing and behaviorally diverse policies.
arXiv AI
Jun 9
A Mixed Diet Makes DINO An Omnivorous Vision Encoder
arXiv:2602. 24181v2 Announce Type: replace-cross Abstract: Pre-trained vision encoders like DINOv2 have demonstrated exceptional performance on unimodal tasks.
arXiv Machine Learning
Jun 9
Stabilizing On-Policy Distillation for MLLM Reasoning with Global Normalization
arXiv:2606. 09091v1 Announce Type: new Abstract: On-policy distillation (OPD) has recently emerged as an important post-training paradigm.
arXiv AI
Jun 9
TLDR: Compressing Audio Tokens for Efficient Autoregressive Text-to-Speech
arXiv:2606. 09019v1 Announce Type: cross Abstract: Codec-based autoregressive (AR) speech language models have achieved strong text-to-speech (TTS) quality by modeling speech as sequences of discrete audio tokens with large pretrained backbones.
arXiv Machine Learning
Jun 9
Differentiable Weightless Controllers: Learning Logic Circuits for Continuous Control
arXiv:2512. 01467v2 Announce Type: replace Abstract: Controlling autonomous systems under real-world conditions often requires policies that can be evaluated with low latency and minimal energy consumption.