When Lower Reconstruction Loss Hurts: Distributionally Robust Refinement for Low-Bit LLM Quantization

Yanlong Zhao et al.

#arXiv #cs.AI #cs.LG #stat.ML

Outperformance Inverse Optimization: Learning Objective Functions that Outperform Agent Decisions

Akira Kitaoka

#arXiv #cs.AI #math.OC #math.ST #stat.ML #stat.TH

I was feeling very creative and made art of Stat as a Were-Spider!

#Regretevator #PixelArt #STAT #Blender #Halloween #Spider #Werewolf #SpookySeason

Connecticut elected officials held a press conference last week to denounce ICE’s recent surge in the state, following the arrests of four young people at Connecticut airports, one a college freshman trying to take a domestic flight.

#STAT #DueProcess #Democratism

When Is Enough Enough in Self-Evolving LLM Systems?

Enoch Yin, Bin Liu, Zhengling Qi

#arXiv #cs.AI #cs.LG #stat.ML

Causally Fair Generation with Large Language Models

Patrik Okanovic, Torsten Hoefler, Drago Plecko

#arXiv #cs.AI #cs.LG #stat.ML

Novacium Unveils Prototype Batteries with Double Energy Capacity for Tactical Applications #France #Batteries #STAT #Novacium #Solaize

CreateScore: Domain-Theory-Informed Bayesian Routing for LLM-Based CV Screening

Rupsa Roy

#arXiv #cs.AI #stat.AP

The 2026 MacArthur Fellows have been announce. It struck me that there were no mathematicians or statisticians among them. I wondered how often that happened, so I turned to Gemini. 🧵1/2
#mathematics #math #statistics #stat #fellowship

Source: buff.ly/fsmAQVG

Learning Multiple Timescales for Goal-Conditioned Reinforcement Learning

Pedro Robles Dutenhefner et al.

#arXiv #cs.AI #stat.ML

Agent Evaluation Reliability: More Tasks Won't (Always) Fix An Agent Leaderboard

Michael Hardy et al.

#arXiv #cs.AI #cs.LG #stat.AP

Targeted Retrieval, Compact Representations: How CoT Reasoning Improves Long-Context Counting

Liang Twist Shan et al.

#arXiv #cs.AI #cs.CL #cs.LG #stat.AP

Targeted Retrieval, Compact Representations: How CoT Reasoning Improves Long-Context Counting

Liang Twist Shan et al.

#arXiv #cs.AI #cs.CL #cs.LG #stat.AP

OTROPE: Optimal Transport-based Robust Off-policy Evaluation for Large Language Models

Liner Xiang, Wenbo Zhang, Hengrui Cai

#arXiv #cs.AI #cs.CL #stat.ML

OTROPE: Optimal Transport-based Robust Off-policy Evaluation for Large Language Models

Liner Xiang, Wenbo Zhang, Hengrui Cai

#arXiv #cs.AI #cs.CL #stat.ML

XU-RS: Explaining Credal Width in Random-Set Language Models

David Achara et al.

#arXiv #cs.AI #stat.ML

🇳🇴 Staten skal stå for millionkrav

#NordicNews #Nyheter #Stat #Innenriks

CoeF-SFL: Preserving Collaborative Server-Client Learning with Enhanced Communication Efficiency

Junwoo Bae, Jin-Hyun Ahn

#arXiv #cs.AI #stat.ML

AmbiModBench: Benchmarking Gene Perturbation Prediction Beyond Shared Responses

Sikai Huang et al.

#arXiv #cs.AI #cs.LG #q-bio.GN #stat.AP

Retrospective Distillation Attribution via Normalized Response Similarity

Minwoo Jang et al.

#arXiv #cs.AI #cs.CL #cs.CR #cs.LG #stat.ML