Home Knowledge Base Sequential Fine-Tuning

Sequential Fine-Tuning

No mentions found

This entity hasn't been tracked yet, or Iris is still building its knowledge base.

Related Articles from SNS

TRACE: Discovering Task-Specific Parameter via Adaptation-Aware Probing for Continual Fine-Tuning

Announce Type: new Abstract: In real-world deployment, LLMs are often adapted continually across tasks to keep LLMs up-to-date in production, where new fine-tuning should preserve previously learned skills. However, indiscriminately mixing tasks can dilute task specialization, while sequential fine-tuning (full-parameter or low rank adaptation) often causes catastrophic forgetting due to destructive overwriting. Replay-based continual tuning and maintaining separate task-specific adapters...

arXiv CS 9d ago

DECA: Decentralizing Block-Wise Adam for Efficient LLM Full-Parameter Fine-Tuning on Non-IID Data

arXiv:2606.03209v1 Announce Type: new Abstract: Fine-tuning large language models (LLMs) in privacy-sensitive and resource-constrained environments remains challenging. Since training data are often distributed across multiple clients, decentralized fine-tuning offers a natural paradigm for collaborative adaptation without a central server. However, enabling full-parameter fine-tuning (FPFT) in this decentralized setting is difficult: FPFT provides strong adaptation capacity but incurs...

arXiv CS 7d ago

Parameter-Efficient Fine-Tuning of Large Pretrained Models for Instance Segmentation Tasks

arXiv:2606.01947v1 Announce Type: new Abstract: Research and applications in artificial intelligence have recently shifted with the rise of large pretrained models, which deliver state-of-the-art results across numerous tasks. However, the substantial increase in parameters introduces a need for parameter-efficient training strategies. Despite significant advancements, limited research has explored parameter-efficient fine-tuning (PEFT) methods in the context of transformer-based models for...

arXiv CS 8d ago

Constrained Flow Optimization via Sequential Fine Tuning for Molecular Design

Announce Type: new Abstract: Adapting generative foundation models, in particular diffusion and flow models, to optimize given reward functions (e.g., binding affinity) while satisfying constraints (e.g., molecular synthesizability) is fundamental for their adoption in real-world scientific discovery applications such as molecular design or protein engineering. While recent works have introduced scalable methods for reward-guided fine-tuning of such models via reinforcement learning and...

arXiv CS 9d ago

G2LoRA: Gradient Orthogonal Low-Rank Adaptation Framework for Graph Continual Learning on Text-Attributed Graphs

Announce Type: new Abstract: LLM-as-Aligner has emerged as a prevalent pre-training paradigm for Text-Attributed Graphs(TAGS), aligning graph and text modalities into a shared embedding space via CLIP-style contrastive learning. While effective on individual downstream tasks, we observe severe catastrophic forgetting when such models are sequentially fine-tuned on streaming tasks. Although parameter-efficient fine-tuning alleviates forgetting to some extent, it remains insufficient to...

arXiv CS 8d ago

Simple Recipe Works: Vision-Language-Action Models are Natural Continual Learners with Reinforcement Learning

arXiv:2603.11653v2 Announce Type: replace Abstract: Continual Reinforcement Learning (CRL) for Vision-Language-Action (VLA) models is a promising direction toward self-improving embodied agents that can adapt in openended, evolving environments. However, conventional wisdom from continual learning suggests that naive Sequential Fine-Tuning (Seq. FT) leads to catastrophic forgetting, necessitating complex CRL strategies. In this work, we take a step back and conduct a systematic study of CRL...

arXiv CS 8d ago

Safety Alignment of LMs via Non-cooperative Games

arXiv:2512.20806v3 Announce Type: replace Abstract: Ensuring the safety of language models (LMs) while maintaining their usefulness remains a critical challenge in AI alignment. Current approaches rely on sequential adversarial training: generating adversarial prompts and fine-tuning LMs to defend against them. We introduce a different paradigm: framing safety alignment as a non-zero-sum game between an Attacker LM and a Defender LM trained jointly via online reinforcement learning.

arXiv CS 8d ago

Representation Collapse in Sequential Post-Training of Large Language Models

Announce Type: new Abstract: Large language models are now adapted through chains of post-training stages rather than through a single instruction-tuning pass. This paper studies whether such sequential post-training gradually compresses internal representations into low-rank, anisotropic, and homogeneous feature spaces. We define a measurement suite for hidden states, logits, token trajectories, and LoRA updates, and we use it to analyze supervised fine-tuning, preference optimization,...

arXiv CS 9d ago

Sequential Subspace Noise Injection Prevents Accuracy Collapse in Certified Unlearning

Announce Type: replace Abstract: Certified unlearning based on differential privacy offers strong guarantees but remains largely impractical: the noisy fine-tuning approaches proposed so far achieve these guarantees but severely reduce model accuracy. We propose sequential noise scheduling, which distributes the noise budget across orthogonal subspaces of the parameter space, rather than injecting it all at once. This simple modification mitigates the destructive effect of noise while...

arXiv CS 9d ago

DiffusionGemma: 4x Faster Text Generation

DiffusionGemma: 4x faster text generation Today, we’re introducing DiffusionGemma, an experimental open model that explores text diffusion, an exceptionally fast approach to text generation. Released under an Apache 2.0 license, this 26B Mixture of Experts (MoE) model moves beyond the sequential token-by-token processing of typical autoregressive Large Language Models (LLMs). Instead, it generates entire blocks of text simultaneously, delivering up to 4x faster text generation on GPUs.

Hacker News 6h ago