TempQuant: Learning Adaptive Temperatures for Quantized Language Models
TempQuant: Learning Adaptive Temperatures for Quantized Language Models — 5 reports from 3 sources so far.
How this story unfolded
Key points0 items Model summary · ordered by when the evidence was published
- Only a handful of reports so far — the model has not distilled any key points yet.
ReportsBy publish time · newer further down
- November 18, 2026 · Wed
- Start
SpatialMind: Adaptive Multi-Level Geometric Fusion for Spatial Reasoning in Multimodal Large Language Models
Original summary arXiv:2611.22415v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) demonstrate promising capabilities in 2D visual understanding, yet remain limited in 3D spa
arXiv cs.CV Original ↗ - Start
TempQuant: Learning Adaptive Temperatures for Quantized Language Models
Original summary arXiv:2611.22128v1 Announce Type: new Abstract: Large language models are increasingly deployed at low precision, yet quantization can degrade their performance. We study how quant
arXiv cs.LG Original ↗ - November 20, 2026 · Fri
- +2d 0h
Learning to Read Events for Exact State Tracking with Frozen Language Models
Original summary arXiv:2611.25211v1 Announce Type: new Abstract: Long event streams require identifying each change and applying the changes in order. We train a selector on a frozen language model
arXiv cs.LG Original ↗ - +2d 0h
Gradients for Interventions and Activation Values for Detection: Targeted Feature Learning in Language Models
Original summary arXiv:2609.32355v2 Announce Type: replace Abstract: Model-internal features can be studied through both their ability to identify a specified concept and their causal effect when m
arXiv cs.CL Original ↗ - +2d 0h
Persistent Sparse Autoencoders: Learning Feature-Specific Timescales in Language Model Representations
Original summary arXiv:2607.17117v3 Announce Type: replace-cross Abstract: Sparse autoencoders (SAEs) decompose language model activations into sparse features, yet these models traditionally encod