arXiv Machine Learning August 31, 2026 By Aaryan Ajay Sharma, Sai Nishanth Padala, Seganrasan Subramanian

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

Read the original on arXiv Machine Learning →

The paper introduces DARTS, a method for tuning decoder representations during model merging. It addresses representation bias in autoregressive decoders by using an entropy‑weighted L1 loss and a per‑position additive bias to correct errors that accumulate across token positions. Experiments on code generation, mathematical reasoning, and instruction following with Llama‑2‑7B show that DARTS improves performance over standard surgery while adding only 0.1% extra parameters.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv AI

6d ago

LEMON: Equivariant Learning over Attention Maps for Zero-Shot Misbehavior Monitoring on New LLMs

arXiv:2610.22723v1 Announce Type: new Abstract: Large language models exhibit misbehaviors that hinder deployment in high-stakes settings. One approach to monitor such failures is to use an external...

By Guy Bar-Shalom, Mor Geva, Fabrizio Frasca, Haggai Maron

llms safety

arXiv AI

Aug 18

UniTAC: Universal Task-Aware Compression via Weighted Distortion Measures

arXiv:2608. 16696v1 Announce Type: cross Abstract: Physical AI systems such as autonomous vehicles and robots rely on timely exchange of high-dimensional sensory signals under tight bandwidth, latency, and energy budgets.

By Homa Esfahanizadeh, Matin Mortaheb, Jinfeng Du, Harish Viswanathan

llms agents computer-vision robotics

arXiv AI

Jun 2

Video Reasoning without Training

arXiv:2510. 17045v2 Announce Type: replace-cross Abstract: Video reasoning using Large Multimodal Models (LMMs) relies on costly reinforcement learning (RL) and verbose chain-of-thought, resulting in substantial computational overhead during both training and inference.

By Deepak Sridhar, Kartikeya Bhardwaj, Jeya Pradha Jeyaraj, Nuno Vasconcelos, Ankita Nayak, Harris Teague

reinforcement-learning fine-tuning multimodal

arXiv Computer Vision

Oct 8

Juno: Taming Predictive Latents for Vision-Language-Action Models

arXiv:2610.09940v1 Announce Type: cross Abstract: Joint-embedding predictive architectures (JEPAs) predict masked or future observations in representation space, offering a natural source of predicti...

By Yuchen Zhu, Chenyi Xu, Yulin Zhang, Gang Xu, Wentao Zhu

rag robotics fine-tuning multimodal

arXiv AI

Jun 16

Improved Baselines with Representation Autoencoders

arXiv:2605. 18324v2 Announce Type: replace-cross Abstract: Representation Autoencoders (RAE) replace traditional VAE with pretrained vision encoders.

By Jaskirat Singh, Boyang Zheng, Zongze Wu, Richard Zhang, Eli Shechtman, Saining Xie

diffusion fine-tuning benchmarks safety

arXiv AI

Jul 14

Depth-Entropy Guided Sampling for Training-Free LLM Reasoning

arXiv:2607. 09693v1 Announce Type: cross Abstract: Reinforcement learning (RL) has become the dominant paradigm for improving the reasoning capabilities of large language models, but it requires expensive training, curated data, and reward signals.

By Zibin Meng, Peng Xie, Kani Chen

llms reinforcement-learning benchmarks

One email a morning, machine-written

Related stories

LEMON: Equivariant Learning over Attention Maps for Zero-Shot Misbehavior Monitoring on New LLMs

UniTAC: Universal Task-Aware Compression via Weighted Distortion Measures

Video Reasoning without Training

Juno: Taming Predictive Latents for Vision-Language-Action Models

Improved Baselines with Representation Autoencoders

Depth-Entropy Guided Sampling for Training-Free LLM Reasoning