National Taiwan University

In sparse-to-dense mesh motion completion, residual priors trained on one geometry family often fail to beat parameter-free harmonic extension, because residual amplitude varies by more than an order of magnitude across families and densities while the target motion is unknown at test time. Cepheid learns only a dimensionless residual structure and recovers physical amplitude from observables plus a lightweight correction fitted on training sources. The unified model stays below harmonic extension on all five evaluated families, cutting error by 15.6% on an unseen cloth sheet and 10.1% on procedural legged bodies, without skeletons, registration, or cross-mesh correspondence.

In sparse-to-dense mesh motion completion, residual priors trained on one geometry family often fail to beat parameter-free harmonic extension, because residual amplitude varies by more than an order of magnitude across families and densities while the target motion is unknown at test time. Cepheid learns only a dimensionless residual structure and recovers physical amplitude from observables plus a lightweight correction fitted on training sources. The unified model stays below harmonic extension on all five evaluated families, cutting error by 15.6% on an unseen cloth sheet and 10.1% on procedural legged bodies, without skeletons, registration, or cross-mesh correspondence.

Autoregressive language models normally learn next-token prediction in a fixed left-to-right order; Max(MI(S;t)) instead ranks target tokens by their mutual information with the source and already-selected targets before training, exposing informative targets earlier. On GPT-style models it reaches 94.96% average accuracy across arithmetic tasks, against 74.84% for next-token prediction and 86.29% for reverse order, close to the 97.33% upper bound from exhaustively testing 24 orders; on WikiText-2 it lowers average perplexity from 13.58 to 10.77. Only the training-target organization changes; architecture and autoregressive decoding stay the same.

Autoregressive language models normally learn next-token prediction in a fixed left-to-right order; Max(MI(S;t)) instead ranks target tokens by their mutual information with the source and already-selected targets before training, exposing informative targets earlier. On GPT-style models it reaches 94.96% average accuracy across arithmetic tasks, against 74.84% for next-token prediction and 86.29% for reverse order, close to the 97.33% upper bound from exhaustively testing 24 orders; on WikiText-2 it lowers average perplexity from 13.58 to 10.77. Only the training-target organization changes; architecture and autoregressive decoding stay the same.

The work proposes EmoRES, a training-free method that discovers that an emotion steering vector decomposes into a shared component moving speech away from neutral expression and a residual component directing generation toward the requested emotion, and controls the two independently; on IEMOCAP, EmoRES outperforms CoCoEmo across all four objective emotion metrics on the frozen IndexTTS-2 and CosyVoice2 backbones, improving rank correlation by 26.13 and 12.97 percentage points and emotion hit rate by 12.95 and 6.92 points, with human evaluation showing up to 35.0% relative improvement in listeners correctly identifying the dominant requested emotion and up to 63.8% naturalness preference in pairwise comparisons.

The work proposes EmoRES, a training-free method that discovers that an emotion steering vector decomposes into a shared component moving speech away from neutral expression and a residual component directing generation toward the requested emotion, and controls the two independently; on IEMOCAP, EmoRES outperforms CoCoEmo across all four objective emotion metrics on the frozen IndexTTS-2 and CosyVoice2 backbones, improving rank correlation by 26.13 and 12.97 percentage points and emotion hit rate by 12.95 and 6.92 points, with human evaluation showing up to 35.0% relative improvement in listeners correctly identifying the dominant requested emotion and up to 63.8% naturalness preference in pairwise comparisons.

The authors built Tri-PvP, an 8,000-sample tri-modal conflict benchmark spanning animal, emotion, environment, and music domains in which image and audio each appear in perceptual form (real photographs or recordings) or propositional form (text-card images or TTS speech) while text is always propositional, evaluated five omni-modal LLMs across four evidence-type conditions, and found that image bias dominates in 18 of 20 model-by-condition bars and that a systematic asymmetry exists: models favor perceptual evidence in vision but propositional evidence in audio, with this bias linearly decodable from early hidden layers and only partially mitigated by contrastive decoding, which introduces a residual text bias.

The authors built Tri-PvP, an 8,000-sample tri-modal conflict benchmark spanning animal, emotion, environment, and music domains in which image and audio each appear in perceptual form (real photographs or recordings) or propositional form (text-card images or TTS speech) while text is always propositional, evaluated five omni-modal LLMs across four evidence-type conditions, and found that image bias dominates in 18 of 20 model-by-condition bars and that a systematic asymmetry exists: models favor perceptual evidence in vision but propositional evidence in audio, with this bias linearly decodable from early hidden layers and only partially mitigated by contrastive decoding, which introduces a residual text bias.