返回首页

端到端

共 46 篇论文

cs.CV自动驾驶端到端

Rectify, Don't Regret: Avoiding Pitfalls of Differentiable Simulation in Trajectory Prediction

This paper addresses critical challenges in autonomous driving trajectory prediction where minor initial deviations in open-loop models cascade into compounding errors, leading to out-of-distribution states. The authors identify a shortcut learning problem in differentiable closed-loop simulators where gradients inadvertently leak future ground truth information into previous predictions, causing non-causal regret instead of genuine recovery. To solve this, they propose a detached receding horizon rollout that severs computation graphs between simulation steps, forcing the model to learn authentic reactive recovery behaviors from drifted states. Comprehensive evaluations on the nuScenes and DeepScenario autonomous driving datasets demonstrate the effectiveness of their approach in achieving genuine trajectory rectification without temporal information leakage.

Anonymous Authors
24 days ago
arXiv 2603.23393v1
cs.CL大语言模型端到端

Off-Policy Value-Based Reinforcement Learning for Large Language Models

This paper addresses the critical challenge of improving data utilization efficiency in reinforcement learning for large language models. The authors propose ReVal, a novel Bellman-update-based method that enables off-policy learning through combining stepwise consistency signals with trajectory-level outcome verification. By supporting replay-buffer-based training, ReVal allows efficient reuse of past trajectories, significantly improving sample efficiency compared to on-policy approaches. Experimental results on mathematical reasoning benchmarks, particularly with DeepSeek-R1-Distill-1.5B, demonstrate that ReVal achieves faster convergence and superior final performance, with improvements of 2.7% on AIME24.

ReVal Team
24 days ago
arXiv 2603.23355v1
cs.CV大语言模型端到端

End-to-End Training for Unified Tokenization and Latent Denoising

Latent diffusion models enable high-fidelity synthesis by operating in learned latent spaces. However, current approaches require complex multi-stage training where tokenizers must be trained separately before diffusion models. This paper proposes UNITE, an autoencoder architecture that unifies tokenization and latent diffusion through a single Generative Encoder with shared weights. The key innovation is treating tokenization and generation as the same latent inference problem under different conditioning regimes. The method introduces a single-stage training procedure that jointly optimizes both tokenization and generation tasks via two forward passes, enabling gradients to jointly shape the latent space for improved visual representation learning.

UNITE Authors
25 days ago
arXiv 2603.22283v1
cs.RO端到端CV

DexDrummer: In-Hand, Contact-Rich, and Long-Horizon Dexterous Robot Drumming

This paper addresses the challenging problem of in-hand, contact-rich, and long-horizon dexterous robot manipulation by proposing drumming as a comprehensive testbed. The DexDrummer framework employs a hierarchical object-centric bimanual policy that combines trajectory planning with residual reinforcement learning corrections, enabling effective sim-to-real transfer. The approach specifically targets dexterous manipulation skills including in-hand control for drumstick stabilization, contact-rich striking interactions, and long-horizon rhythmic coordination across multiple drums. By integrating these three challenging aspects into a single complex task, this work advances the field of robotic dexterity and manipulation planning.

DexDrummer Team
25 days ago
arXiv 2603.22263v1
cs.CL大语言模型端到端

Confidence-Based Decoding is Provably Efficient for Diffusion Language Models

This paper addresses the decoding efficiency challenge in diffusion language models (DLMs), which have emerged as promising alternatives to autoregressive models for language generation. The research focuses on confidence-based decoding strategies that adaptively select and unmask tokens based on prediction confidence during the generation process. The authors develop a theoretical analysis framework specifically for an entropy sum-based strategy that continues unmasking tokens until cumulative entropy exceeds a threshold. This work provides the first formal theoretical guarantees demonstrating the efficiency of confidence-based decoding in diffusion-based text generation, offering insights into how adaptive token selection can improve sampling efficiency compared to traditional decoding approaches.

Anonymous Authors
25 days ago
arXiv 2603.22248v1
cs.RO端到端CV

Make Tracking Easy: Neural Motion Retargeting for Humanoid Whole-body Control

This paper addresses the challenge of transferring human motion data to humanoid robots by proposing Neural Motion Retargeting (NMR), a novel framework that transforms static geometric mapping into a dynamics-aware learned process. The approach uses Clustered-Expert Physics Refinement (CEPR) with VAE-based motion clustering to group heterogeneous movements into latent motifs, significantly reducing computational overhead for reinforcement learning experts that project and repair noisy human motion data. Through Hessian analysis, the authors demonstrate that traditional optimization-based retargeting is inherently non-convex and prone to local optima, leading to physical artifacts. By reformulating the problem as learning data distribution rather than optimizing solutions, the framework achieves smooth, physically plausible whole-body robot control.

NMR Research Team
25 days ago
arXiv 2603.22201v1
cs.AI大语言模型端到端

CayleyPy-4: AI-Holography. Towards analogs of holographic string dualities for AI tasks

This paper presents the fourth installment of the CayleyPy project, applying AI methods to explore large graphs through a novel discrete version of holographic string dualities. The research demonstrates that many modern AI tasks, particularly GPT-style language models and reinforcement learning systems, can be modeled as predicting particle trajectories on graphs. For Cayley graphs of the symmetric group S_n, the authors establish a dual description in terms of discrete strings and propose string holographic images as natural candidates for data embeddings, extending the complexity equals volume principle from AdS/CFT to AI applications. This work hypothesizes potential extensions of such dualities across a range of AI systems, suggesting more efficient computational approaches for language modeling and general AI tasks.

CayleyPy Project Team
25 days ago
arXiv 2603.22195v1
cs.CL大语言模型端到端

Enhancing Document-Level Machine Translation via Filtered Synthetic Corpora and Two-Stage LLM Adaptation

This paper addresses the challenge of improving document-level machine translation using Large Language Models. The authors propose a two-stage fine-tuning strategy that augments training data by converting summarization data into document-level parallel data using LLMs. To ensure data quality, they filter the synthetic corpus using multiple metrics including sacreBLEU, COMET, and LaBSE-based cosine similarity. The approach tackles two key challenges: the scarcity of large-scale document-level parallel data and the tendency of LLMs to generate hallucinations and omissions. By leveraging LLMs' strength in modeling contextual information, this method aims to improve coherence across sentences in translation tasks.

Ireh Kim +2
25 days ago
arXiv 2603.22186v1
cs.LG大语言模型端到端

Revisiting Quantum Code Generation: Where Should Domain Knowledge Live?

This paper investigates how to effectively incorporate domain knowledge into LLM-based code generation systems for quantum software development. The researchers evaluate various strategies including parameter-specialized fine-tuned models and general-purpose LLMs enhanced with retrieval-augmented generation and agent-based inference mechanisms. Using the Qiskit-HumanEval benchmark, they compare different approaches to quantum code generation with Qiskit frameworks. The study finds that modern general-purpose LLMs with advanced inference techniques consistently outperform specialized fine-tuned baselines, achieving approximately 47% pass@1 performance. These findings suggest that general-purpose models with retrieval and execution feedback mechanisms may be more suitable for evolving software ecosystems compared to domain-specific specialized models.

Anonymous Authors
25 days ago
arXiv 2603.22184v1
cs.CV自动驾驶端到端

Closed-Loop Verbal Reinforcement Learning for Task-Level Robotic Planning

This paper presents a Verbal Reinforcement Learning framework for interpretable task-level planning in mobile robots operating under execution uncertainty. The approach employs a closed-loop architecture where Behavior Trees are iteratively refined by a Large Language Model, guided by structured feedback from a Vision-Language Model critic that observes robot execution. Unlike traditional reinforcement learning, policy updates occur at the symbolic planning level without gradient-based optimization, enabling transparent reasoning and human-interpretable policy evolution. The framework is validated on a real mobile robot performing multi-stage manipulation and navigation tasks, demonstrating effective handling of execution uncertainty through iterative refinement.

Anonymous Authors
25 days ago
arXiv 2603.22169v1
cs.RO端到端CV

ROBOGATE: Adaptive Failure Discovery for Safe Robot Policy Deployment via Two-Stage Boundary-Focused Sampling

This paper presents ROBOGATE, a deployment risk management framework for safe robot policy deployment in industrial settings. The framework combines physics-based simulation with a two-stage adaptive sampling strategy to efficiently discover failure boundaries in high-dimensional operational parameter spaces. Stage 1 uses Latin Hypercube Sampling across an 8-dimensional parameter space, while Stage 2 applies boundary-focused sampling in the 30-70% success rate transition zone. Evaluated using NVIDIA Isaac Sim with Newton physics on Franka Panda and UR5e robots performing pick-and-place tasks across 30,000 experiments, the system employs logistic regression for risk modeling to ensure safe robot manipulation policy deployment.

Robogate Research Team
25 days ago
arXiv 2603.22126v1
cs.CL大语言模型端到端

On the Failure of Topic-Matched Contrast Baselines in Multi-Directional Refusal Abliteration

This paper investigates the effectiveness of topic-matched contrast baselines in multi-directional refusal abliteration for instruction-tuned language models. The research focuses on extracting refusal-mediating directions from the residual stream activation space of the Qwen 3.5 2B model using per-category matched prompt pairs, Self-Organizing Map extraction, and Singular Value Decomposition orthogonalization. The key finding reveals that while unmatched contrast successfully achieves complete refusal elimination across tested weight levels and layers, topic-matched contrast produces no functional refusal directions. This work highlights the importance of contrast baseline construction as a critical methodological consideration rather than an implementation detail in model abliteration research.

Anonymous
25 days ago
arXiv 2603.22061v1
cs.CL大语言模型端到端

Dual-Space Knowledge Distillation with Key-Query Matching for Large Language Models with Vocabulary Mismatch

This paper addresses the challenge of knowledge distillation between large language models with different tokenizers. The authors systematically analyze the attention mechanism of Dual-Space Knowledge Distillation with Cross-Model Attention (DSKD-CMA), revealing its strengths and limitations through token alignment probing and visualization. They propose DSKD-CMA-GA, a novel method leveraging Generative Adversarial learning to better align mismatched key-query distributions across models. Experimental results demonstrate consistent improvements in text generation quality as measured by ROUGE-L scores, offering a more transparent and effective approach to compressing large language models for efficient deployment.

Anonymous
25 days ago
arXiv 2603.22056v1
cs.CL大语言模型端到端

Retrieving Climate Change Disinformation by Narrative

This paper addresses the challenge of detecting climate disinformation narratives by re-framing traditional detection as a retrieval task. Rather than relying on fixed taxonomies that cannot accommodate emerging narratives, the approach ranks texts by alignment with a given narrative core message. The proposed SpecFi framework generates hypothetical documents to bridge abstract narrative descriptions with concrete textual instantiations, using community summaries from graph-based detection as few-shot examples for generation. The method achieves a MAP of 0.505 on the CARDS dataset without accessing narrative labels. Additionally, the paper introduces narrative variance, an embedding-based difficulty metric, and demonstrates its utility through partial correlation analysis for understanding narrative complexity in climate disinformation detection.

Anonymous Authors
25 days ago
arXiv 2603.22015v1
cs.AI大语言模型端到端

TREX: Trajectory Explanations for Multi-Objective Reinforcement Learning

This paper presents TREX, a Trajectory-based Explainability framework designed for Multi-Objective Reinforcement Learning (MORL). The work addresses the limitation that traditional Explainable Reinforcement Learning (XRL) methods are typically tailored for single scalar rewards and fail to provide explanations when agents optimize multiple conflicting objectives simultaneously. The proposed approach enables agents to explicitly reason about trade-offs between different objectives and generates interpretable explanations for the decision-making process behind objective trade-offs. By focusing on trajectory-level explanations, TREX provides insights into how agents navigate decision spaces when balancing competing objectives in complex real-world scenarios.

Multiple Authors
25 days ago
arXiv 2603.21988v1
cs.CL大语言模型端到端

SecureBreak: A Dataset Towards Safe and Secure Models

Large language models are becoming pervasive core components in many real-world applications. As a consequence, security alignment represents a critical requirement for their safe deployment. Although previous related works focused primarily on model architectures and alignment methodologies, these approaches alone cannot ensure the complete elimination of harmful generations. This concern is reinforced by the growing body of scientific literature showing that attacks, such as jailbreaking and prompt injection, can bypass existing security alignment mechanisms. As a consequence, additional security strategies are needed both to provide qualitative feedback on the robustness of the obtained security alignment at the training stage, and to create an ultimate defense layer to block unsafe outputs possibly produced by deployed models. To provide a contribution in this scenario, this paper introduces SecureBreak, a safety-oriented dataset designed to support the development of AI-driven security solutions for language models.

SecureBreak Team
25 days ago
arXiv 2603.21975v1
cs.AI大语言模型端到端

Demystifying Reinforcement Learning for Long-Horizon Tool-Using Agents: A Comprehensive Recipe

This paper presents a systematic empirical study on scaling Reinforcement Learning for Large Language Model agents in complex, multi-turn environments. Using TravelPlanner as a testbed, the authors decompose the agentic RL design space along five critical axes including reward shaping, model scaling, data composition, algorithm selection, and environmental stability. Their controlled experiments reveal key insights: reward and algorithm choices are scale-dependent with smaller models benefiting from staged rewards while larger models converge with simpler dense rewards, approximately 1K training samples with balanced difficulty mixture represents the optimal training budget, and environmental stability is crucial for preventing policy degradation. The work provides a practical recipe for developing autonomous LLM agents capable of long-horizon tool orchestration and planning.

TravelPlanner Research Team
25 days ago
arXiv 2603.21972v1
cs.CL大语言模型端到端

SLURP-TN: Resource for Tunisian Dialect Spoken Language Understanding

This paper introduces SLURP-TN, a comprehensive spoken language understanding resource specifically designed for the Tunisian dialect. The dataset comprises 4165 sentences recorded from 55 native speakers, totaling approximately 5 hours of acoustic material. By translating sentences from six SLURP domains, the authors address the critical gap in SLU resources for low-resource languages. The research develops baseline Automatic Speech Recognition and SLU models that leverage deep neural networks and pre-trained language models to extract semantic information from speech utterances in task-oriented dialogue systems. This work enables the Tunisian-speaking population to benefit from recent advances in natural language processing and speech recognition technology.

Elyadata Research Team
25 days ago
arXiv 2603.21940v1
cs.CL大语言模型端到端

P^2O: Joint Policy and Prompt Optimization

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a powerful paradigm for enhancing the reasoning capabilities of Large Language Models (LLMs). However, vanilla RLVR suffers from inefficient exploration, particularly when confronting hard samples that yield near-zero success rates. In such scenarios, the reliance on sparse outcome rewards typically results in zero-advantage estimates, effectively starving the model of supervision signals despite the high informational value of these instances. To address this, we propose P^2O, a novel framework that synergizes Prompt Optimization with Policy Optimization. P^2O identifies hard samples during training iterations and leverages the GeneticPareto (GEPA) prompt optimization algorithm to evolve prompt templates that guide the model toward discovering successful trajectories.

P^2O Authors
25 days ago
arXiv 2603.21877v1
cs.RO端到端具身智能

Sim-to-Real of Humanoid Locomotion Policies via Joint Torque Space Perturbation Injection

This paper presents a novel sim-to-real approach for training humanoid robot locomotion policies by injecting state-dependent perturbations into joint torque space during simulation. Unlike traditional domain randomization methods that randomize fixed parameters, the proposed approach uses neural networks to generate complex, state-dependent perturbations that simulate nonlinear actuator dynamics and contact compliance. The method achieves superior robustness against unseen reality gaps, demonstrating successful transfer from simulation to real-world humanoid deployment without requiring additional training. Experimental validation confirms that policies trained with this perturbation injection technique can handle complex real-world scenarios that standard randomization cannot capture.

Anonymous Authors
25 days ago
arXiv 2603.21853v1
第 1 / 3 页下一页