IST Austria Distributed Algorithms and Systems Lab

ISTA-DASLab's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Articles

helcig 

updated a model about 4 hours ago

ISTA-DASLab/lossless-lm-dev

Updated about 4 hours ago

softmax 

authored a paper about 2 months ago

WUSH: Near-Optimal Adaptive Transforms for LLM Quantization

Paper • 2512.00956 • Published Nov 30, 2025 • 23

soroushtabesh 

authored a paper 2 months ago

CAGE: Curvature-Aware Gradient Estimation For Accurate Quantization-Aware Training

Paper • 2510.18784 • Published Oct 21, 2025 • 1

ionutmodo 

authored 2 papers 4 months ago

Unified Scaling Laws for Compressed Representations

Paper • 2506.01863 • Published Jun 2, 2025 • 19

Optimizers Qualitatively Alter Solutions And We Should Leverage This

Paper • 2507.12224 • Published Jul 16, 2025 • 1

SpiridonSunRotator 

authored a paper 4 months ago

Bridging the Gap Between Promise and Performance for Microscaling FP4 Quantization

Paper • 2509.23202 • Published Sep 27, 2025 • 28

softmax 

authored 7 papers 6 months ago

Scalable Mechanistic Neural Networks

Paper • 2410.06074 • Published Oct 8, 2024 • 1

MARLIN: Mixed-Precision Auto-Regressive Parallel Inference on Large Language Models

Paper • 2408.11743 • Published Aug 21, 2024 • 1

QuEST: Stable Training of LLMs with 1-Bit Weights and Activations

Paper • 2502.05003 • Published Feb 7, 2025 • 42

Flow Matching for Discrete Systems: Efficient Free Energy Sampling Across Lattice Sizes and Temperatures

Paper • 2503.08063 • Published Mar 11, 2025 • 1

Quartet: Native FP4 Training Can Be Optimal for Large Language Models

Paper • 2505.14669 • Published May 20, 2025 • 78

Accurate generation of chemical reaction transition states by conditional flow matching

Paper • 2507.10530 • Published Jul 14, 2025 • 1

The Geometry of LLM Quantization: GPTQ as Babai's Nearest Plane Algorithm

Paper • 2507.18553 • Published Jul 24, 2025 • 41

ionutmodo 

authored 3 papers 8 months ago

Error Feedback Can Accurately Compress Preconditioners

Paper • 2306.06098 • Published Jun 9, 2023

MicroAdam: Accurate Adaptive Optimization with Low Space Overhead and Provable Convergence

Paper • 2405.15593 • Published May 24, 2024 • 1

SVD-Free Low-Rank Adaptive Gradient Optimization for Large Language Models

Paper • 2505.17967 • Published May 23, 2025 • 17

dalistarh 

authored a paper 8 months ago

Quartet: Native FP4 Training Can Be Optimal for Large Language Models

Paper • 2505.14669 • Published May 20, 2025 • 78

soroushtabesh 

authored a paper 8 months ago

Quartet: Native FP4 Training Can Be Optimal for Large Language Models

Paper • 2505.14669 • Published May 20, 2025 • 78

BlackSamorez 

authored a paper 8 months ago

Quartet: Native FP4 Training Can Be Optimal for Large Language Models

Paper • 2505.14669 • Published May 20, 2025 • 78

dalistarh 

authored a paper 10 months ago

Hogwild! Inference: Parallel LLM Generation via Concurrent Attention

Paper • 2504.06261 • Published Apr 8, 2025 • 110