Signals 4 · free daily AI digest

DARTS: Decoder-Aware Representation Tuning via Surgery for Model Merging

Paper recorded by Signals 4 on 2026-08-28 in cs.LG. Abstract reproduced from arXiv; link to the original below.

Published 2026-08-28 on arXiv · recorded by Signals 4 on 2026-08-31

Category: cs.LG · 机器学习 · first seen 2026-08-31

Abstract

Model merging combines multiple task-specific fine-tuned LLMs into a single multi-task model without additional training. However, merged models are known to suffer from representation bias: systematic drift between the merged model's hidden states and those of each individual source model. Prior work (Yang et al., 2024a) study and mitigate this bias for encoder-based vision models using a lightwe

Read on arXiv →

#205 most recent of 215 cs.LG papers we have recorded · ↑ newer: Advancing Interaction-Sensitive Feature Selection: Novel Relief-Based · ↓ older: REPLICANT: Learning Policies for Evading and Hardening Malware Detecto
Cite this page: DARTS: Decoder-Aware Representation Tuning via Surgery for Model Merging: the #205 most recent of 215 cs.LG papers we have recorded (as of 2026-08-28). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/darts-decoder-aware-representation-tuning-via-surgery-for-model-merging.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.LG papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions