Trendoday

Steerable Multi-Objective Group-Relative Preference Optimization with Jointly Trained Low-Rank Adapters

Language model deployment often requires different trade-offs between competing objectives as user preferences change, yet standard post-training methods typically produce a single policy for a fixed

  • Upvotes7
–Rank now
#15Peak rank
3Days on list
141Score · 7d
Nov 9, 2026First seen
Rank · 7 days

About this paper

Language model deployment often requires different trade-offs between competing objectives as user preferences change, yet standard post-training methods typically produce a single policy for a fixed objective weighting. We introduce LambdaMix, a new parameter efficient method for learning a preference conditioned family of policies with group-relative online reinforcement learning. LambdaMix jointly trains one low-rank adapter per objective over a frozen base model. One preference vector selects the adapter mixture that generates responses and weights the separately normalized rewards used to update the adapters. A single training run supports changing preferences at inference without…

Upvotes
7
Authors
2
Published
Nov 6, 2026

Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.

Trending history

Steerable Multi-Objective Group-Relative Preference Optimization with Jointly Trained Low-Rank Adapters was first seen on Hugging Face · Daily papers on Nov 9, 2026. Since then it has appeared in 15 checks on 3 different days. Its best position was #15 of 30, reached on Nov 10, 21:28 UTC. It dropped off the list after Nov 11, 01:28 UTC.

Rank history

Position on Hugging Face · Daily papers at every check (lower is better).

#1#11#20#30 21:2804:2811:2818:2801:28 Nov 9, 21:28 UTC · #27Nov 9, 23:28 UTC · #27Nov 10, 01:28 UTC · #25Nov 10, 03:28 UTC · #25Nov 10, 05:28 UTC · #24Nov 10, 07:28 UTC · #23Nov 10, 09:28 UTC · #25Nov 10, 11:28 UTC · #22Nov 10, 13:28 UTC · #20Nov 10, 15:28 UTC · #19Nov 10, 17:28 UTC · #17Nov 10, 19:28 UTC · #16Nov 10, 21:28 UTC · #15Nov 10, 23:28 UTC · #15Nov 11, 01:28 UTC · #15

Last 14 days

Best rank per day (UTC).

Nov 3today

Metric history

Platform metric as reported by Hugging Face.

04711 21:2804:2811:2818:2801:28 Nov 9, 21:28 UTC · 7Nov 9, 23:28 UTC · 7Nov 10, 01:28 UTC · 7Nov 10, 03:28 UTC · 7Nov 10, 05:28 UTC · 7Nov 10, 07:28 UTC · 7Nov 10, 09:28 UTC · 7Nov 10, 11:28 UTC · 7Nov 10, 13:28 UTC · 7Nov 10, 15:28 UTC · 7Nov 10, 17:28 UTC · 9Nov 10, 19:28 UTC · 11Nov 10, 21:28 UTC · 11Nov 10, 23:28 UTC · 11Nov 11, 01:28 UTC · 11

Questions

Is Steerable Multi-Objective Group-Relative Preference Optimization with Jointly Trained Low-Rank Adapters trending on HF Daily Papers right now?

Not at the moment. It was last on the list on Nov 11, 01:28 UTC, after 3 days of trending.

What is the highest rank Steerable Multi-Objective Group-Relative Preference Optimization with Jointly Trained Low-Rank Adapters reached?

#15 on Hugging Face · Daily papers, on Nov 10, 21:28 UTC. Trendoday checks this list every 120 minutes.

How long has Steerable Multi-Objective Group-Relative Preference Optimization with Jointly Trained Low-Rank Adapters been trending?

It was first seen on Nov 9, 2026 and has been on the list on 3 days (15 checks) since.