Deploying a joint audio-video diffusion transformer for real-time, interactive generation normally requires two essential modifications: block-autoregressive attention, so frames can be emitted before the whole clip is finished, and few-step sampling, so each block is cheap. Conventionally, the streaming video literatu...
Large language model agents can invoke tools fluently, but enterprise workflows demand more than selecting the right tools: actions must strictly comply with organizational policies, tool feedback often conceals hidden side effects under partial observability, and long-horizon tasks require persistent state tracking ac...
An avatar that holds a conversation should decide what to say and to move while saying it, yet these abilities live in separate model families: spoken dialogue models produce speech without motion, and co-speech motion models produce motion only from audio handed to them. The standard remedy is a cascade that first gen...
Chengqian Ma, Wei Tao, Hao-Yu Zhang et al.· 0 citations
A multi-pass flow blending pipeline synthesizes frame-aligned transition audio, circumventing the scarcity of natural intra-utterance transitions, and dual-stage Valence-Arousal-Dominance conditioning guides prosodic planning in the LLM and acoustic realization in the flow decoder via frame-level VAD embeddings.
Tian-Chi Liu, Ze-Yang Song, Tian-Rui Wang et al.· 5 citations
This work proposes $\delta$-Vision, which replaces repeated Transformer evolution of visual tokens with lightweight low-rank adapters that construct layer-wise visual memories while preserving all visual tokens for text retrieval, and achieves higher accuracy than visual token pruning baselines at comparable or lower c...
Jing-Di Lei, Junxian Li, Di Zhang et al.· 0 citations
This work proposesSkill-$\alpha, a reinforcement learning method that learns a unified policy for progressive skill generation and introduces a novel rollback reward that evaluates each edit by comparing downstream execution under the original and edited skills on an anchored query.
Junhao Shen, Zhan-Qiu Zhang, Yi-Wen Guo et al.· 1 citation
CONDUIT, a training-free refresh policy that unifies single- and multi-image reuse as residual-stream restoration, is proposed, building on norm-weighted attention and an accessible pre-output cached-value-norm proxy, then applies empirical image-level relevance amplification before one global selection.
Pengan Chen, Kai-Sheng Zheng, Liang Hong et al.· 0 citations
This work introduces GameWAM, to its knowledge the first WAM for native closed-loop gameplay and GUI control and uncovers Low-Frequency Action Source Imprinting (LASI), in which low-frequency components of the sampled action source systematically steer coarse generated camera motion under fixed conditioning, revealing...
Yun-Cheng Guo, Zhan-Qiu Zhang, Yi-Wen Guo et al.· 0 citations
Omni-modal dialogue models can understand multimodal inputs and synthesize spoken replies, but a spoken answer still leaves the agent visually absent. We introduce \textbf{Ex-Omni-2D}, a framework that answers a multimodal query with coordinated text, personalized speech, and reference-conditioned video. The dialogue m...
Haoyu Zhang, Zhipeng Li, Xiaoying Tang et al.· 0 citations
This work constructs two human-verified benchmarks, VRQABench for controllable spatial lookahead and OpenWorldQA for open-domain physical prediction, and proposes Privileged-Future On-Policy Self-Distillation (PF-OPSD), a model that outperforms baseline by 10.6% and 10.9% on VRQABench and OpenWorldQA, respectively, whi...
Automated agent design improves agent harnesses through iterative revision, evaluation, and feedback summarization. Existing methods are largely candidate-centric: cross-round experience is organized around candidate agents, which leaves the repair progress implicit. This causes inefficient repair targeting, slow conso...
Lekang Jiang, Bohan Tang, Stephan M. Goetz et al.· 0 citations
MemDefrag, a training-free and model-agnostic framework that uses a middle-layer tracing signal to conduct memory defragmentation (rank, reorder, and filter memories), and applies an informativeness-guided proportional forgetting mechanism once capacity is exceeded, is proposed.
Ruiyi Yan, Zhuoyuan Mao, Yiwen Guo· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
