Image de couverture de livre

Multi-Adapter Representation Interventions via Energy Calibration

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Yu, Manjiang, Li, Hongji, Chen, Junwei, Li, Xue, Singh, Priyanka, Cao, Yang, Hu, Lijie
Format:	Preprint
Publié:	2026
Sujets:	Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

PIXEL: Adaptive Steering Via Position-wise Injection with eXact Estimated Levels under Subspace Calibration
par: Yu, Manjiang, et autres
Publié: (2025)

Towards Reasoning-Preserving Unlearning in Multimodal Large Language Models
par: Li, Hongji, et autres
Publié: (2025)

Adaptive Token-Weighted Differential Privacy for LLMs: Not All Tokens Require Equal Protection
par: Yu, Manjiang, et autres
Publié: (2025)

High Order Reasoning for Time Critical Recommendation in Evidence-based Medicine
par: Yu, Manjiang, et autres
Publié: (2024)

FaithSteer-BENCH: A Deployment-Aligned Stress-Testing Benchmark for Inference-Time Steering
par: Ding, Zikang, et autres
Publié: (2026)

Predicting LLM Output Length via Entropy-Guided Representations
par: Xie, Huanyi, et autres
Publié: (2026)

Adaptive Multi-Subspace Representation Steering for Attribute Alignment in Large Language Models
par: Jiang, Xinyan, et autres
Publié: (2025)

LTMSformer: A Local Trend-Aware Attention and Motion State Encoding Transformer for Multi-Agent Trajectory Prediction
par: Yan, Yixin, et autres
Publié: (2025)

ROME: Memorization Insights from Text, Logits and Representation
par: Li, Bo, et autres
Publié: (2024)

MGCBS: An Optimal and Efficient Algorithm for Solving Multi-Goal Multi-Agent Path Finding Problem
par: Tang, Mingkai, et autres
Publié: (2024)

Nonlinearity as Rank: Generative Low-Rank Adapter with Radial Basis Functions
par: Ouyang, Yihao, et autres
Publié: (2026)

MACD: Multi-Agent Clinical Diagnosis with Self-Learned Knowledge for LLM
par: Li, Wenliang, et autres
Publié: (2025)

Global Evolutionary Steering: Refining Activation Steering Control via Cross-Layer Consistency
par: Jiang, Xinyan, et autres
Publié: (2026)

1%>100%: High-Efficiency Visual Adapter with Complex Linear Projection Optimization
par: Yin, Dongshuo, et autres
Publié: (2026)

AdaFuse: Accelerating Dynamic Adapter Inference via Token-Level Pre-Gating and Fused Kernel Optimization
par: Li, Qiyang, et autres
Publié: (2026)

Beyond Scalars: Evaluating and Understanding LLM Reasoning via Geometric Progress and Stability
par: Jiang, Xinyan, et autres
Publié: (2026)

Introspection Adapters: Training LLMs to Report Their Learned Behaviors
par: Shenoy, Keshav, et autres
Publié: (2026)

PoLAR: Polar-Decomposed Low-Rank Adapter Representation
par: Lion, Kai, et autres
Publié: (2025)

Learning Adapter Rank via Symmetry Breaking
par: Doyle, Cooper, et autres
Publié: (2025)

Parameter-Efficient Fine-Tuning With Adapters
par: Chen, Keyu, et autres
Publié: (2024)

On the Role of Language Representations in Auto-Bidding: Findings and Implications
par: Zhu, Guanyu, et autres
Publié: (2026)

Visual Self-Fulfilling Alignment: Shaping Safety-Oriented Personas via Threat-Related Images
par: Yang, Qishun, et autres
Publié: (2026)

Federated Cross-Modal Retrieval with Missing Modalities via Semantic Routing and Adapter Personalization
par: Zhou, Hefeng, et autres
Publié: (2026)

DM-Adapter: Domain-Aware Mixture-of-Adapters for Text-Based Person Retrieval
par: Liu, Yating, et autres
Publié: (2025)

Variational Adapter for Cross-modal Similarity Representation
par: Wei, WenZhang, et autres
Publié: (2026)

STAMP: Spatial-Temporal Adapter with Multi-Head Pooling
par: Shook, Brad, et autres
Publié: (2025)

Att-Adapter: A Robust and Precise Domain-Specific Multi-Attributes T2I Diffusion Adapter via Conditional Variational Autoencoder
par: Cho, Wonwoong, et autres
Publié: (2025)

Effective LoRA Adapter Routing using Task Representations
par: Dhasade, Akash, et autres
Publié: (2026)

Representation Interventions Enable Lifelong Knowledge Memory Control in LLMs
par: Liu, Xuyuan, et autres
Publié: (2025)

MeetBench-XL: Calibrated Multi-Dimensional Evaluation and Learned Dual-Policy Agents for Real-Time Meetings
par: Hu, Yuelin, et autres
Publié: (2026)

A Multi-Modal CNN-LSTM Framework with Multi-Head Attention and Focal Loss for Real-Time Elderly Fall Detection
par: Zhou, Lijie, et autres
Publié: (2026)

Soft-Prompting with Graph-of-Thought for Multi-modal Representation Learning
par: Yang, Juncheng, et autres
Publié: (2024)

Dissecting Representation Misalignment in Contrastive Learning via Influence Function
par: Hu, Lijie, et autres
Publié: (2024)

LoRA-Switch: Boosting the Efficiency of Dynamic LLM Adapters via System-Algorithm Co-design
par: Kong, Rui, et autres
Publié: (2024)

PlaneCycle: Training-Free 2D-to-3D Lifting of Foundation Models Without Adapters
par: Yu, Yinghong, et autres
Publié: (2026)

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning
par: Zhang, Lin, et autres
Publié: (2025)

Scaling-Aware Adapter for Structure-Grounded LLM Reasoning
par: Jing, Zihao, et autres
Publié: (2026)

Sparse Adapter Fusion for Continual Learning in NLP
par: Zeng, Min, et autres
Publié: (2026)

Long-tailed Medical Diagnosis with Relation-aware Representation Learning and Iterative Classifier Calibration
par: Pan, Li, et autres
Publié: (2025)

Flora: Low-Rank Adapters Are Secretly Gradient Compressors
par: Hao, Yongchang, et autres
Publié: (2024)