Decision Transformer (DT) has demonstrated strong performance in various offline reinforcement learning (RL) tasks by conditioning action generation on expected future returns and historical trajectories. However, treating expected future returns as the condition provides an incomplete description of the future, as tra...
Chang-Xu Ni, Yi-Yang Ni, Jun Li et al.· 0 citations
This work introduces FuseReg, which replaces heuristic feature selection with training over random subsets of encoder layers, and theoretically analyze the underlying mechanism: subset sampling preserves the full-layer latent mean in expectation while explicitly penalizing sensitivity to cross-layer disagreement.
Hong-Yang Du, Yun-Fei Xie, Jun-Jie Ye et al.· 1 citation
The results suggest that local action-comparison supervision can complement temporal prediction by encouraging JEPA-based representations to retain both long-horizon temporal structure and fine-grained distinctions among locally observed actions for offline zero-shot control.
FARM (Fundamental Agentic Reward Model for Multi-task Wireless Network Optimization), a reward-space transfer framework that shifts cross-task knowledge reuse from policy space to trajectory-level decision evaluation, is proposed.
Fei-Ran You, Chang-Xu Ni, Hao-Zhe Ma et al.· 0 citations
The Global Verifier (GLOVE) is proposed, a framework that introduces a new design dimension for LLM memory systems by establishing a relative notion of truth and substantially improves agent success rates, suggesting a robust pathway to cognitive agents capable of self-evolving.
Across three text-to-video backbones, Carnator consistently achieves higher cache-hit end-to-end acceleration than the evaluated cross-request baselines despite more selective cache acceptance, reaching up to 2.17 times speedup while maintaining competitive generation quality.
Xing-Kun Yin, Xue-Bin Tang, Ming-Kun Xu et al.· 0 citations
NebastianSD is presented, a many-for-many, or M-for-N, speculative decoding system that organizes draft and target workers into independently schedulable resource pools and dynamically reconstructs stage-specific batches from shared request pools.
Professional graphic design is a long-horizon agentic task in which structured, editable artifacts emerge from many interdependent actions, yet outcomes admit no reliable programmatic oracle. We introduce a continual adaptation framework in which a frozen frontier model operates professional design software through mor...
Hong-Yang Du, Lan Yan, Christian Flores et al.· 0 citations
Counterfactual Relevance for On-Policy Distillation is introduced, which operationalizes task relevance through a paraphrase-calibrated counterfactual sensitivity margin and establishes CROP as a model-internal, contrast-specific method for allocating token-level supervision.
HACO is proposed, a runtime control scheme that treats each role request as a reliability-constrained selection problem over candidate agent instances, each coupling a role type, an LLM, and a concrete execution environment.
A Mobile Reasoning-as-aService (MORES) framework that treats reasoning as a computational service accessible to edge devices over wireless networks, and focuses on implicit reasoning, which achieves an approximately 18% improvement in system throughput over the baseline Soft Actor-Critic (SAC) algorithm.
Guanchen Liu, Hongyang Du, Kaibin Huang· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.