System-1 Decision Models directly make structured probabilistic decisions over query-specified options given a state in a single forward pass, without autoregressively generating reasoning trajectories or textual responses. Recent evaluations cover diverse tasks but often rely on existing benchmarks, where prior exposu...
Attention-based rerankers score each candidate by the attention mass that retrieval heads route to it from the question, but the question, serving as a fixed query, carries limited information for locating relevant evidence. We propose Re$^3$Rank, a listwise reranker built on reasoning-conditioned retrieval heads (RRHe...
Rui-Yi Yan, Zhuo-Yuan Mao, Yugo Murawaki et al.· 0 citations
Test-time scaling improves large language models through additional computation, but how to adapt the topology of internal computation to individual inputs remains underexplored. Existing approaches largely fix recurrent or parallel architectures during training, or reconfigure frozen models along a single structural a...
Instruction-based text-to-speech (TTS) offers control over voice characteristics and speech expression through interfaces including voice cloning and text-based voice design. Voice cloning reproduces a reference voice, whereas text-based voice design creates a voice from a natural-language description. However, neither...
Jun-Chuan Zhao, Cheng-Lin Xu, Wei Zeng et al.· 0 citations
Large language model agents are emerging as an important new class of users of desktop applications. However, existing desktop interfaces were designed for human end users or application developers, leaving agents to interpret visual controls or discover and compose low-level software operations. This mismatch can hind...
Following the idea of model merging, it is shown that on a packed audio-video backbone the two capabilities can be acquired in parallel, yielding few-step, streaming audio-video whose image quality tracks the bidirectional teacher.
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...
Motion-Omni is presented, an end-to-end framework in which a spoken dialogue model natively outputs explicit facial expression together with hand, upper-body and lower-body motion, generated directly from the hidden states that produce the speech.
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.· 6 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.· arXiv.org· 0 citations
Streaming omni-modal models must decide what and when to answer from the video chunks and synchronized audio observed so far. Visual cues often support an interpretation before an utterance or sound event is complete. If that interpretation enters memory as a fact, later reasoning can keep relaying it even after audio...
En-Jun Du, Si-Yi Liu, Zi-Yu Zheng et al.· 1 citation
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
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.