gradient-conflict

Tag

Cards List
#gradient-conflict

A Local Perturbation Theory for Cross-Domain Interference and Recovery in Multi-Domain RL

Hugging Face Daily Papers · 2026-06-01 Cached

This paper proposes a local perturbation theory to explain cross-domain interference in multi-domain RL for LLMs, showing that interference is driven by a second-order damage term in a low-dimensional conflict subspace, and demonstrates that brief domain refresh or training-free rollback can selectively recover lost capabilities.

0 favorites 0 likes
#gradient-conflict

Decentralized Instruction Tuning: Conflict-Aware Splitting and Weight Merging

Hugging Face Daily Papers · 2026-06-01 Cached

MERIT introduces conflict-aware splitting and weight merging for decentralized instruction tuning, achieving improved performance without gradient synchronization across partitions.

0 favorites 0 likes
#gradient-conflict

Conflict-Aware Additive Guidance for Flow Models under Compositional Rewards

arXiv cs.AI · 2026-05-22 Cached

The paper identifies off-manifold drift in guided flow models under compositional rewards and proposes Conflict-Aware Additive Guidance (CAR), a lightweight method that dynamically resolves gradient conflicts to improve generation fidelity without retraining.

0 favorites 0 likes
#gradient-conflict

DualOptim+: Bridging Shared and Decoupled Optimizer States for Better Machine Unlearning in Large Language Models

arXiv cs.LG · 2026-05-22 Cached

Introduces DualOptim+, an optimization framework for LLM unlearning that uses shared base states and decoupled delta states to balance forgetting and retaining objectives, with a quantized variant for reduced memory.

0 favorites 0 likes
← Back to home

Submit Feedback