CKT-WAM: Parameter-Efficient Context Knowledge Transfer Between World Action Models

• URL: http://arxiv.org/abs/2605.06247v1
• Date: Thu, 07 May 2026 13:26:51 GMT
• Title: CKT-WAM: Parameter-Efficient Context Knowledge Transfer Between World Action Models
• Abstract summary: World action models (WAMs) provide a powerful generative framework for embodied control.<n>We propose textbfCKT-WAM, a framework that transfers teacher WAM's knowledge into a student WAM.<n>CKT-WAM consistently improves zero-shot generalization and achieves the best overall performance on LIBERO-Plus.
• Score: 45.34156934993461
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: World action models (WAMs) provide a powerful generative framework for embodied control, yet transferring knowledge across heterogeneous WAMs remains challenging due to mismatched latent interfaces, high adaptation cost, and the rigidity of conventional distillation objectives. We propose \textbf{CKT-WAM}, a parameter-efficient \textbf{C}ontext \textbf{K}nowledge \textbf{T}ransfer framework that transfers teacher WAM's knowledge into a student WAM through a compact context in the text embedding space, rather than output imitation or dense hidden-state matching. Specifically, CKT-WAM extracts intermediate teacher hidden states, reduces the number of tokens via compressors' learnable-query cross attention (LQCA), and transforms them through an always-on generalized adapter, a lightweight router, and sparsely activated specialized adapters. The resulting context is then appended to the student's conditioning textual embeddings, thereby injecting the transferred knowledge into the student with minimal architectural modification. Experiments show that CKT-WAM consistently improves zero-shot generalization and achieves the best overall performance on LIBERO-Plus, reaching 86.1\% total success rate with only 1.17\% trainable parameters, while approaching full fine-tuning performance. Beyond simulation, CKT-WAM also demonstrates strong real-world long-horizon manipulation ability, achieving the best average success rate of 83.3\% across four multi-step and long-horizon tasks. Code is available at https://github.com/YuhuaJiang2002/CKT-WAM.

Related papers

• AC-VLA: Robust Out-of-Distribution Action Execution via Compositional Learning [52.47988016454267]
  Vision-Language-Action (VLA) models excel at end-to-end robotic manipulation but struggle with out-of-distribution (OOD) generalization.<n>We identify two mutually reinforcing modes: emphtrajectory overfitting, where models overfit to holistic trajectory patterns rather than compositional sub-skill semantics; and emphperceptual shortcut, where action tokens over-rely on wrist-view textures at the expense of global spatial grounding.<n>We introduce textbfAC-VLA, a plug-and-play Action Compositional learning
  arXiv  Detail & Related papers  (2026-07-17T07:51:03Z)
• Beyond Attention Magnitude: Leveraging Inter-layer Rank Consistency for Efficient Vision-Language-Action Models [75.27089289058613]
  We introduce textbfTIES (textbfTau-guided textbfInter-layer textbfEfficient textbfSelection), a dynamic framework guided by inter-layer token ranking consistency.<n>On the CogACT + SIMPLER benchmark, TIES improves average success rates by 6% while reducing token usage by 78%, and demonstrate strong generalization across diverse decoders and benchmarks.
  arXiv  Detail & Related papers  (2026-03-26T02:13:03Z)
• BOFA: Bridge-Layer Orthogonal Low-Rank Fusion for CLIP-Based Class-Incremental Learning [84.56022893225422]
  Class-Incremental Learning (CIL) aims to continually learn new categories without forgetting previously acquired knowledge.<n>Applying vision-language models such as CLIP to CIL poses two major challenges: (1) adapting to downstream tasks often requires additional learnable modules, increasing model complexity and susceptibility to forgetting; and (2) while multi-modal representations offer complementary strengths, existing methods have yet to fully realize their potential in effectively integrating visual and textual modalities.
  arXiv  Detail & Related papers  (2025-11-14T15:51:40Z)
• Asymmetric Cross-Modal Knowledge Distillation: Bridging Modalities with Weak Semantic Consistency [16.550957851406014]
  Cross-modal Knowledge Distillation has demonstrated promising performance on paired modalities with strong semantic connections.<n>We investigate a general and effective knowledge learning concept under weak semantic consistency, dubbed Asymmetric Cross-modal Knowledge Distillation (ACKD)<n>We propose a framework, namely SemBridge, integrating a Student-Friendly Matching module and a Semantic-aware Knowledge Alignment module.
  arXiv  Detail & Related papers  (2025-11-12T02:24:24Z)
• Put Teacher in Student's Shoes: Cross-Distillation for Ultra-compact Model Compression Framework [48.66685912952879]
  We introduce Edge ultra-lIte BERT framework (EI-BERT) with a novel cross-distillation method.<n>We achieve a remarkably compact BERT-based model of only 1.91 MB - the smallest to date for Natural Language Understanding (NLU) tasks.
  arXiv  Detail & Related papers  (2025-07-07T03:38:09Z)
• Ken Utilization Layer: Hebbian Replay Within a Student's Ken for Adaptive Knowledge Tracing [11.25951282067287]
  KUL-KT is a biologically inspired architecture for knowledge tracing (KT)<n>It combines Hebbian memory encoding with gradient-based consolidation in a scalable, input-agnostic framework.<n>We introduce two key innovations: (i) a time-decaying Hebbian memory update that enables graceful forgetting, and (ii) a novel Loss-aligned Internal Target (LIT) method to compute an ideal internal state.
  arXiv  Detail & Related papers  (2025-06-18T00:06:28Z)
• Prompt-OT: An Optimal Transport Regularization Paradigm for Knowledge Preservation in Vision-Language Model Adaptation [5.296260279593993]
  Vision-language models (VLMs) such as CLIP demonstrate strong performance but struggle when adapted to downstream tasks.<n>We propose an optimal transport (OT)-guided prompt learning framework that mitigates forgetting by preserving the structural consistency of feature distributions.<n>Our approach enforces joint constraints on both vision and text representations, ensuring a holistic feature alignment.
  arXiv  Detail & Related papers  (2025-03-11T21:38:34Z)
• Multi-Level Optimal Transport for Universal Cross-Tokenizer Knowledge Distillation on Language Models [81.74999702045339]
  Multi-Level Optimal Transport (MultiLevelOT) is a novel approach that advances the optimal transport for universal cross-tokenizer knowledge distillation.<n>Our method aligns the logit distributions of the teacher and the student at both token and sequence levels.<n>At the token level, MultiLevelOT integrates both global and local information by jointly optimizing all tokens within a sequence to enhance robustness.
  arXiv  Detail & Related papers  (2024-12-19T04:51:06Z)
• A Contrastive Knowledge Transfer Framework for Model Compression and Transfer Learning [5.239675888749389]
  This paper proposes a novel Contrastive Knowledge Transfer Framework (CKTF) CKTF enables the transfer of sufficient structural knowledge from the teacher to the student by optimizing multiple contrastive objectives. CKTF consistently outperforms the existing KT works by 0.04% to 11.59% in model compression and by 0.4% to 4.75% in transfer learning.
  arXiv  Detail & Related papers  (2023-03-14T02:45:41Z)
• Adapted Multimodal BERT with Layer-wise Fusion for Sentiment Analysis [84.12658971655253]
  We propose Adapted Multimodal BERT, a BERT-based architecture for multimodal tasks. adapter adjusts the pretrained language model for the task at hand, while the fusion layers perform task-specific, layer-wise fusion of audio-visual information with textual BERT representations. In our ablations we see that this approach leads to efficient models, that can outperform their fine-tuned counterparts and are robust to input noise.
  arXiv  Detail & Related papers  (2022-12-01T17:31:42Z)
• LANA: Towards Personalized Deep Knowledge Tracing Through Distinguishable Interactive Sequences [21.67751919579854]
  We propose Leveled Attentive KNowledge TrAcing (LANA) to predict students' responses to future questions. It uses a novel student-related features extractor (SRFE) to distill students' unique inherent properties from their respective interactive sequences. With pivot module reconstructed the decoder for individual students and leveled learning specialized encoders for groups, personalized DKT was achieved.
  arXiv  Detail & Related papers  (2021-04-21T02:57:42Z)
• Efficient Crowd Counting via Structured Knowledge Transfer [122.30417437707759]
  Crowd counting is an application-oriented task and its inference efficiency is crucial for real-world applications. We propose a novel Structured Knowledge Transfer framework to generate a lightweight but still highly effective student network. Our models obtain at least 6.5$times$ speed-up on an Nvidia 1080 GPU and even achieve state-of-the-art performance.
  arXiv  Detail & Related papers  (2020-03-23T08:05:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.