Gradient Projection

Follow this topic Ask about this topic

Momentum

3 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 16

Oct 6, 2026cs.CV

UP-MOPD: Update Projection in Multi-Teacher On-Policy Distillation

On-policy distillation from multiple teachers combines expertise from different domains in a single student, but conflicting gradients can hinder this integration. Gradient corrections directly constrain parameter updates under plain SGD. With optimizers such as AdamW, however, momentum, adaptive scaling, and weight decay can turn a corrected gradient into an update that increases a domain loss to first order. To address this gap, we propose Update Projection for Multi-Teacher On-Policy Distillation (UP-MOPD). UP-MOPD lets the original mixed gradient update the optimizer state and generate a candidate displacement, then projects only violating candidates before they are committed to the parameters. The projection gives the unique feasible update closest to the candidate in Euclidean distance. In experiments combining medical and general domains, UP-MOPD improves IFEval-loose accuracy late in training by 2.96 points over vanilla M-OPD. It achieves an average score of 60.03 across eight metrics, compared with 59.00 for gradient projection and 59.15 for update rejection. On a public benchmark covering mathematics, code, and instruction following, it achieves the best average across six tasks (32.67), leads on LiveCodeBench v5, and ties for the best IFEval result.These results support projecting optimizer updates to reduce interference between domains.

Taojie Zhu, Jing Jin, Yuan Xia +8

Tsinghua University · Ant Group · Zhejiang University

Language Model Distillation Gradient Projection Multi-Teacher Knowledge Distillation On-Policy Distillation

Sep 28, 2026cs.LG

See it, Say it, Sorted: Mechanistic Diagnosis and Parameter-Space Mitigation of Emergent Misalignment in LLMs

Safety-aligned LLMs can exhibit emergent misalignment (EM): narrow domain adaptation unexpectedly triggers catastrophic safety failures across unrelated domains. Prior static analyses leave training dynamics unmapped, while existing defenses rely on heuristics that degrade utility. We present a dynamic, second-order geometric study of EM. Tracking training trajectories reveals that directional Hessian curvature concentrates sharply on semantic pivot tokens. Grassmannian projections show that, in most settings, harmful-safe gap widens mainly because safe-gradient overlap declines. Leveraging these insights, we introduce a parameter-level Geometric Mitigation Framework that orthogonally projects empirical harmful gradient subspace out of parameter updates. On Qwen2.5-14B-IT, our defense suppresses free-generation EM by up to 80.0%; across the other three of four open-weight instruction-based model families (3B--20B), where single-layer behavioral EM is already near zero, teacher-forced evaluation shows same harmful subspace controls the conditional support of frozen EM responses. Crucially, these diagnostics unmask the illusion of behavioral safety: the same subspace remains measurable and steerable in models where behavioral EM is near zero. Code: https://github.com/WeiqiaoQUE/mechanistic-emergent-misalignment.

Weiqiao Que, Ruizhe Li, Chengyu Wang +3

School of Computer Science and Technology, East China Normal University, China · School of Computer Science, University of Birmingham, UK · Alibaba Group, China +2

Emergent Misalignment in Language Models LLM Safety Alignment Mechanistic Interpretability Gradient Projection

Sep 28, 2026cs.LG

PMOPD: Task Ordering, Cycling, and Parameter-Update Subspace Protection in Multi-Teacher On-Policy Distillation

Multi-teacher on-policy distillation (MOPD) has emerged as a popular post-training paradigm for integrating specialized capabilities in frontier language models. Existing OPD research has primarily focused on optimizing single-task distillation through objective design, distillation scope, and teacher signal construction, whereas MOPD must aggregate multiple capabilities in shared parameters and address the resulting capability seesaw, in which improving one domain suppresses capabilities acquired from another. Inspired by the distinctive update geometry of OPD, we find that parameter updates from different tasks rapidly concentrate in their respective low-dimensional subspaces during MOPD, providing a direct geometric basis for identifying and controlling cross-task interference. We therefore propose PMOPD (Projection-based Multi-Teacher On-Policy Distillation), which constructs subspace memories from the cumulative parameter displacements of different tasks and projects both gradients and optimizer updates to remove components that interfere with protected task directions. We further develop a lightweight conflict probe to characterize task interactions and guide task ordering, together with a cycling strategy that balances subspace estimation and timely task revisitation. Experiments on representative Code, Reason, and Math tasks show that PMOPD improves every evaluated capability over MOPD, raising the average score across the three tasks by 2.54 points on Qwen2.5-7B and 2.09 points on Llama-3.1-8B. These consistent gains establish geometry-aware optimization as an effective and transferable approach to balanced multi-teacher distillation.

Youzhi Liu, Ruobing Zheng, Boyuan Tong +5

Ant Group

Gradient Interference Multi-Task Learning Language Model Distillation Gradient Projection Multi-Teacher Knowledge Distillation On-Policy Distillation

Sep 13, 2026cs.LG

Tackling Failure Modes of PINNs and PIKANs Using Conflict-Free Gradients

Scientific machine learning methods such as physics-informed neural networks (PINNs) increasingly rely on domain decomposition for better scalability while solving partial differential equations (PDEs) over complex geometries, yet the resulting composite loss comprising residual, boundary, and interface terms is highly susceptible to conflicting gradients that degrade training. This work bridges domain decomposition with projection-based gradient surgery to systematically mitigate such conflicts in 2D and 3D settings. We evaluate two existing projection-based algorithms, PCGrad and ConFIG, and identify their performance degradation in specific scenarios such as 3D domains with multiple overlapping interfaces. To address this limitation, we propose Norm-PCGrad, a normalized variant that achieves state-of-the-art accuracy across a range of 2D and 3D domain decomposition problems. Across the benchmarks considered, Norm-PCGrad consistently achieves the lowest relative

L_2

error compared to training without gradient surgery as well as to existing algorithms such as PCGrad and ConFIG, while incurring negligible additional computational overhead. To improve computational efficiency of domain decomposition frameworks such as Extended PINN (XPINN), we propose replacing vanilla PINNs in selected subdomains with separable architectures such as Separable PINN (SPINN), reducing the computational cost from quadratic (or cubic) to linear. We additionally demonstrate that gradient surgery extends to physics-informed Kolmogorov-Arnold Networks (PIKANs), yielding substantial accuracy improvements for 3D domain decomposition and confirming the generality of the proposed approach across network architectures.

Sidharth S. Menon, Irina Tezaur, Ameya D. Jagtap

Aerospace Engineering Department, Worcester Polytechnic Institute, Worcester, MA 01609, USA. · Sandia National Laboratories, 7011 East Ave, Livermore, CA 94550, USA.

PDE Solving Gradient Interference Gradient Projection Physics-Informed ML

Sep 1, 2026cs.LG

Gradient-Update Mismatch: Rethinking Conflict-Free Training of Physics-Informed Neural Networks

Training Physics-Informed Neural Networks (PINNs) requires jointly optimizing physics residual and initial/boundary condition loss terms, which often induce conflicting gradients. Gradient surgery methods mitigate this issue by constructing directions from loss-specific gradients to reduce conflict before optimizer transformation. However, even when the constructed direction is conflict-free, this property may not be preserved after optimizer transformation. Let

a_t

denote the direction constructed by gradient surgery,

u_t

the optimizer proposal, and

\mathcal{C}_t

the conflict-free cone induced by the loss-specific gradients. We show that modern optimizers can transform

a_t

through mechanisms such as historical state, adaptive scaling, preconditioning, or decoupled weight decay, so

a_t \in \mathcal{C}_t

does not generally imply

u_t \in \mathcal{C}_t

. We refer to this optimizer-induced discrepancy in conflict-freeness between

a_t

and

u_t

as Gradient-Update Mismatch (GUM). Accordingly, we propose Gradient-Update Alignment (GUA), which projects

u_t

onto

\mathcal{C}_t

to obtain the aligned update

p_t

and applies

p_t

to the parameters. When the optimizer maintains internal state, GUA further adjusts this state toward targets reconstructed from the applied update. We conduct extensive experiments and find that GUM is widespread across momentum, adaptive, and curvature-based optimizers, with conflict rates reaching up to 86.3%. Across all PINN settings, GUA achieves conflict-free applied updates and consistently improves various gradient surgery methods, reducing the relative

L_2

error by up to 98.2% in individual settings. Data and code are available at https://github.com/JingXiao10/GUA.

Jing Xiao, Xinhai Chen, Qinglin Wang +5

Laboratory of Digitizing Software for Frontier Equipment, National University of Defense Technology, Changsha 410073, China · National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, Changsha 410073, China · School of Computer Science and Technology, National University of Defense Technology, Changsha 410073, China

Neural Network Optimization Gradient Interference Gradient Projection Physics-Informed ML

Jul 13, 2026cs.CL

Unified Gradient Projection: Language-Balanced Continual Learning for Multilingual Low-Resource ASR

Large-scale pretrained ASR models such as Whisper exhibit strong multilingual capabilities. However, fine-tuning on low-resource languages often causes catastrophic forgetting. Although continual learning mitigates this issue, existing methods struggle to regulate cross-task interference in multilingual settings, where dominant languages bias optimization. We propose Unified Gradient Projection (UGP), which constrains parameter updates using reference gradients from language-balanced replay in a unified projection space. By equalizing per-language contributions in the projection, UGP reduces dominant-language bias and improves cross-lingual stability. We further show that combining gradient-level projection with data-level replay yields complementary gains in stability and plasticity. Across diverse low-resource language groups and model scales, UGP enables effective adaptation while substantially mitigating forgetting. On Whisper-large-v3, it achieves near-zero average forgetting.

Ziang Ren, Guodong Lin, Yuchen Ai +2

Department of Electronic Engineering, Tsinghua University, China

Automatic Speech Recognition Gradient Projection Low-Resource Speech Recognition Catastrophic Forgetting Multilingual ASR

Jul 1, 2026cs.CV

Rosetta: Composable Native Multimodal Pretraining

Achieving true artificial general intelligence requires foundation models capable of integrating new modalities without forgetting prior knowledge. However, accommodating continuous generative objectives alongside discrete understanding tasks causes severe gradient conflicts. Existing architectures, including standard Mixture-of-Experts (MoE), are highly susceptible to representation overwriting. Even structurally partitioned paradigms like Mixture-of-Transformers (MoT) remain vulnerable to catastrophic forgetting, severely impeding multimodal scalability. In this work, we introduce Rosetta, a composable native multimodal pretraining framework designed for seamless and non-destructive modality expansion. Rosetta adopts a modular paradigm where core foundational knowledge is preserved within global shared experts, while modality-specific capabilities are distributed across plug-and-play experts. To guarantee non-destructive composition, we propose Momentum-Anchored Orthogonal Projection (MAOP). MAOP leverages the optimizer's momentum state as an implicit semantic anchor, selectively neutralizing conflicting gradient components from new modalities while preserving synergistic updates. Extensive evaluations demonstrate that, while standard MoE and MoT architectures suffer catastrophic forgetting of previously acquired knowledge, Rosetta robustly preserves established language and visual understanding. Furthermore, it delivers superior image generation and unlocks cross-modal synergy, paving the way for truly composable and unified multimodal foundation models. To facilitate further multimodal research, we release our code and checkpoints to the community. Project page at https://rosetta-lmm.github.io/.

Xiangyue Liu, Zijian Zhang, Miles Yang +3

HKUST · Tencent Hunyuan

Unified Multimodal Models Multimodal Pretraining Multimodal Generation Gradient Projection Multimodal Foundation Models Continual Learning for VLMs+2

Jun 29, 2026cs.RO

Trajectory Optimization for Collision-Aware Redundant Robotic Multi-Axis Additive Manufacturing by Constrained Gradient Projection

Redundant robotic multi-axis additive manufacturing (MAAM) enables support-free and conformal fabrication, but trajectory optimization for long-horizon paths remains challenging under strict deposition-position constraints and time-varying collision constraints. This work proposes a computational framework for collision-aware trajectory optimization in redundant robotic MAAM. We first formulate nozzle-workpiece relative kinematics using a relative Jacobian, and develop a differentiable SDF-based collision model that captures fabrication-induced geometry evolution and provides optimization gradients. The deposition position is then enforced as a hard waypoint-wise equality constraint through iterative projection onto the self-motion manifold, with the loss gradient restricted to the corresponding tangent space. Experiments on an 8-DOF robotic MAAM platform with diverse long-horizon support-free and conformal toolpaths show that our method maintains a mean nozzle-position error below 10μm, reduces maximum joint jerk by up to

77.6\%

, and eliminates all sampled collision and orientation violations. Compared with the SQP-based baseline, it achieves up to a 10.2x speedup and improved convergence. Physical fabrication experiments further verify that the resulting smooth, collision-free trajectories enable successful printing of complex geometries with fewer visible deposition artifacts.

Zhikai Shen, Jiasheng Qu, Chenyu Xu +4

Manufacturing Constrained Motion Planning Trajectory Optimization Trajectory Generation Robotics Gradient Projection+3

Jun 2, 2026cs.LG

PURGE: Projected Unlearning via Retain-Guided Erasure

We propose PURGE, a machine unlearning algorithm built on a simple but an under-exploited observation: continual learning (CL) and machine unlearning (MU) which are fundamentally dual problems. CL tries to learn new tasks without forgetting old ones; MU tries to erase specific data without hurting retained performance representing the same underlying tension in opposite directions. PURGE leverages this duality by adapting gradient projection from A-GEM (Chaudhry et al., 2019) so that every unlearning step is constrained to not increase the retain-set loss. On top of this, it performs multi-layer representation erasure, pushing forget-set activations in intermediate layers towards the retain distribution to remove information from hidden representations rather than just suppressing it at the output. A key design choice is the retain-confusion target: rather than pushing forget outputs toward the uniform distribution, which we found to be surprisingly easy for membership inference attacks to detect, we instead target the model's natural confusion pattern on retain data. This makes the unlearned model hard to distinguish from one retrained from scratch. Two self-regulating stopping criteria (a retain-loss budget and a forget-accuracy target) let the algorithm decide on its own when to stop, removing the need for manual epoch tuning. In experiments on five datasets (CIFAR-10, MNIST, SVHN, STL10, PathMNIST) across 22 class-level forgetting tasks, PURGE consistently keeps retain accuracy above 96% while achieving MIA AUROC close to 0.5 (the ideal), outperforming gradient ascent, KL-uniform, and several published baselines on the privacy-utility frontier.

Vedant Jawandhia, Daksh Ahuja, Ghufran Alam Siddiqui +3

1BITS Pilani, Pilani Campus, India

Privacy-Preserving ML Gradient Projection Machine Unlearning

Jun 1, 2026cs.LG

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

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 resolve task interference and ineffective knowledge transfer. In this work, we study graph continual learning for LLM-as-Aligner models on TAGs, with the goal of mitigating interference while promoting positive transfer across tasks. This setting introduces two fundamental challenges: (1) heterogeneous downstream tasks induce shifting optimization objectives, hindering unified fine-tuning; and (2) graph and text encoders exhibit different sensitivities to adaptation, making uncoordinated updates prone to misalignment. To address these challenges, we propose G2LoRA, a continual learning framework for TAGs. G2LoRA unifies node-, link-, and graph-level tasks under a single graph--text alignment objective, and enables consistent optimization across domain/class/task incremental modes. To reduce task interference while encouraging positive transfer, G2LoRA performs category-aware gradient projection in structured subspaces, resolving conflicting updates and enabling conditional backward transfer to balance forward and backward knowledge flow. To further prevent cross-modal drift, G2LoRA introduces gradient magnitude modulation to coordinate update rates between graph and text encoders. Extensive experiments on benchmark datasets demonstrate that G2LoRA consistently outperforms strong baselines across different backbone architectures, achieving superior continual performance and transferability.

Yuhan Wang, Yibo Ding, Yutong Ye +4

School of Computer Science and Engineering, Beihang University Beijing, China · Department of Statistics, Columbia University New York, NY, USA · College of Computer Science, Beijing University of Technology Beijing, China

Continual Learning Low-Rank Adaptation Text-Attributed Graph Learning Gradient Projection

May 18, 2026cs.AI

Interference-Aware Multi-Task Unlearning

Machine unlearning aims to remove the contribution of designated training data from a trained model while preserving performance on the remaining data. Existing work mainly focuses on single-task settings, whereas modern models often operate in multi-task setups with shared backbones, where removing supervision for one task or instance can unintentionally affect others. We introduce multi-task unlearning with two settings: full-task unlearning, which removes a target instance from all tasks, and partial-task unlearning, which removes supervision only from selected tasks. We show that shared parameters couple the forget and retain sets, causing task-level interference on non-target tasks and instance-level interference on other instances. To address this issue, we propose an interference-aware framework that combines task-aware gradient projection, which constrains updates within task-specific subspaces, with instance-level gradient orthogonalization, which reduces conflicts between forget and retain signals. Experiments on two multi-task computer vision benchmarks across five tasks show that our method achieves effective unlearning while maintaining strong generalization, reducing UIS compared with the strongest baseline by 30.3% in full-task unlearning and 52.9% in partial-task unlearning.

Ying-Hua Huang, Rui Fang, Hsi-Wen Chen +1

National Taiwan University

Gradient Projection Machine Unlearning

Apr 22, 2026cs.CV

Projected Gradient Unlearning for Text-to-Image Diffusion Models: Defending Against Concept Revival Attacks

Machine unlearning for text-to-image diffusion models aims to selectively remove undesirable concepts from pre-trained models without costly retraining. Current unlearning methods share a common weakness: erased concepts return when the model is fine-tuned on downstream data, even when that data is entirely unrelated. We adapt Projected Gradient Unlearning (PGU) from classification to the diffusion domain as a post-hoc hardening step. By constructing a Core Gradient Space (CGS) from the retain concept activations and projecting gradient updates into its orthogonal complement, PGU ensures that subsequent fine-tuning cannot undo the achieved erasure. Applied on top of existing methods (ESD, UCE, Receler), the approach eliminates revival for style concepts and substantially delays it for object concepts, running in roughly 6 minutes versus the ~2 hours required by Meta-Unlearning. PGU and Meta-Unlearning turn out to be complementary: which performs better depends on how the concept is encoded, and retain concept selection should follow visual feature similarity rather than semantic grouping.

Aljalila Aladawi, Mohammed Talha Alam, Fakhri Karray

Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE. · University of Waterloo, Ontario, Canada.

Diffusion Model Fine-Tuning Diffusion Model Unlearning Gradient Projection Machine Unlearning T2I Diffusion Models Diffusion Models

Apr 20, 2026cs.LG

SafeAnchor: Preventing Cumulative Safety Erosion in Continual Domain Adaptation of Large Language Models

Safety alignment in large language models is remarkably shallow: it is concentrated in the first few output tokens and reversible by fine-tuning on as few as 100 adversarial examples. This fragility becomes critical in real-world deployment, where models undergo sequential adaptation across domains such as medicine, law, and code, causing safety guardrails to erode cumulatively. Yet all existing safety-preserving methods target only single-task fine-tuning, leaving the multi-domain sequential setting entirely unaddressed. We introduce SafeAnchor, a framework that anchors safety in place throughout continual adaptation. SafeAnchor first identifies low-rank safety subspaces in LoRA parameter space via Fisher Information eigendecomposition, then constrains domain-specific gradient updates to the orthogonal complement of these subspaces, and finally monitors for residual safety drift with threshold-triggered corrective replay. Evaluated on Llama-2-7B-Chat and Mistral-7B-Instruct across a three-domain pipeline and eight benchmarks, SafeAnchor retains 93.2% of original safety alignment, outperforming all baselines by 18-42 points, while matching unconstrained fine-tuning to within 1.5 points on domain tasks.

Dongxin Guo, Jikun Wu, Siu Ming Yiu

The University of Hong Kong, Hong Kong, China · Brain Investing Limited, Hong Kong, China

Continual Learning for LLMs LLM Fine-Tuning LLM Safety Alignment Domain Adaptation for LLMs Gradient Projection

Apr 17, 2026cs.LG

AEGIS: Anchor-Enforced Gradient Isolation for Knowledge-Preserving Vision-Language-Action Fine-Tuning

Fine-tuning pre-trained Vision-Language Models (VLMs) for robotic manipulation introduces a fundamental stability-plasticity dilemma: continuous flow-matching action experts backpropagate concentrated, low-rank regression gradients into transformer backbones trained on high-dimensional cross-entropy objectives. This cross-modal gradient asymmetry rapidly degrades pre-trained visual reasoning. Existing solutions either disconnect continuous gradient flow via stop-gradients or constrain updates via LoRA, which restricts update rank but remains directionally blind to semantic corruption; both typically rely on mixed-batch VQA co-training, doubling training compute. We introduce AEGIS (Anchor-Enforced Gradient Isolation System), a buffer-free, layer-wise orthogonal gradient projection framework enabling continuous flow-matching fine-tuning while isolating pre-trained representations from destructive parameter updates. Prior to training, AEGIS estimates per-layer Gaussian activation statistics from pre-training data as a static reference anchor. During fine-tuning, a closed-form Wasserstein-2 transport penalty generates an anchor-restoration gradient through the active computation graph. A sequential dual-backward pass applies layer-wise Gram-Schmidt orthogonalization, projecting task gradients onto the orthogonal complement of the restoration vector during directional conflict. We establish an exact energy preservation bound for layer-wise orthogonal projection, showing that AEGIS sheds only 0.62% of gradient energy empirically while halting cumulative feature drift. On PaliGemma2-3B fine-tuned on the LIBERO manipulation benchmark, AEGIS fully preserves pre-trained Visual Question Answering performance and baseline holdout loss while matching continuous action convergence, without replay buffers, teacher models, or co-training data.

Guransh Singh

Independent Researcher

VLM Adaptation Robotic Manipulation Gradient Projection Vision-Language-Action Models Catastrophic Forgetting

Sep 25, 2025cs.LG

Task-Agnostic Federated Continual Learning via Replay-Free Gradient Projection

Federated continual learning (FCL) enables collaborative model training across distributed clients on sequentially arriving tasks without revisiting past data. However, existing approaches often suffer from catastrophic forgetting, rely on replay buffers or generative models that may violate privacy constraints, or assume knowledge of task identities during inference. We propose FedProTIP (Federated Projection-based Continual Learning with Task Identity Prediction), a replay-free FCL framework that maintains shared task-specific feature subspaces across clients. Each client extracts low-rank core bases from intermediate activations using randomized singular value decomposition, capturing dominant feature directions associated with the current task. These bases are transmitted to the server and aggregated to construct global task subspaces that capture shared feature directions across clients without requiring data sharing. During training, client updates are projected onto the orthogonal complement of previously learned subspaces to reduce cross-task interference and mitigate catastrophic forgetting. The learned subspaces are also reused during inference to estimate task identity via subspace relevance, enabling task-agnostic prediction without requiring explicit task labels. Experiments on CIFAR100, ImageNet-R, and DomainNet demonstrate that FedProTIP consistently outperforms state-of-the-art federated continual learning baselines while maintaining lower training time, memory footprint, and communication cost.

Seohyeon Cha, Huancheng Chen, Haris Vikalo

Department of Electrical and Computer Engineering The University of Texas at Austin

Federated Continual Learning Gradient Projection Federated Learning

Date pendingcs.LG

Denoising as Projection: Constrained Optimization with Gradient-Guided Diffusion

Diffusion models are increasingly used not only for sampling from learned data distributions, but also for generating samples that optimize task-specific objectives. A common approach is to guide the reverse diffusion process using gradients of an external objective. However, when the data distribution is supported on a structured feasible set, such as a manifold or a constraint set, gradient guidance can move samples away from the learned data geometry. In this paper, we study a simple projected-gradient-guided diffusion update based on the observation that the Stein denoising operator can act as an approximate projection onto the data geometry. The proposed update incorporates the objective gradient inside the denoising step, yielding an inference-time method that uses only a pretrained denoiser and gradient evaluations. We analyze this update as an inexact projected-gradient method for constrained optimization over learned feasible geometries. Our theory covers three settings: linear manifolds, compact convex feasible sets, and compact Riemannian submanifolds. In all these settings, we prove descent and finite-time convergence guarantees. Numerical experiments support the theoretical interpretation and illustrate how the proposed update balances objective descent with preservation of the learned geometry.

Runyu Zhang, Jiawei Zhang, Gioele Zardini +2

MIT · University of Wisconsin–Madison

Riemannian Optimization Diffusion Guidance Gradient Projection Constrained Optimization Inference-Time Guidance