arXiv:2602.22508v2 Announce Type: replace
Abstract: Large Language Models (LLMs) often produce incorrect answers on multi-hop question answering even when the reasoning trace already contains a correct intermediate conclusion. We attribute this gap to…
arXiv:2605.10261v1 Announce Type: new
Abstract: TCAV (Testing with Concept Activation Vectors) is an interpretability method that assesses the alignment between the internal representations of a trained neural network and human-understandable, high-le…
arXiv:2602.09534v2 Announce Type: replace
Abstract: Realistic talking-head video generation is critical for virtual avatars, film production, and interactive systems. Current methods struggle with nuanced emotional expressions due to the lack of fine-…
arXiv:2605.03929v3 Announce Type: replace-cross
Abstract: Stem retrieval, the task of matching missing stems to a given audio submix, is a key challenge currently limited by models that discard temporal information. We introduce PHALAR, a contrastive …
arXiv:2605.08729v1 Announce Type: new
Abstract: Motion, speech, and sound effects are fundamental elements of human-centric videos, yet their heterogeneous temporal characteristics make joint generation highly challenging. Existing audio-video generat…
arXiv:2602.22779v2 Announce Type: replace
Abstract: Tokenization in video models, typically through patchification, generates an excessive and redundant number of tokens. This severely limits video efficiency and scalability. While recent trajectory-b…
arXiv:2605.10267v1 Announce Type: new
Abstract: In industrial procurement, an LLM answer is useful only if it survives a standards check: recommended material must match operating condition, every parameter must respect a regulated threshold, and no p…
arXiv:2502.06830v5 Announce Type: replace-cross
Abstract: Probabilistic intraday electricity price forecasting is becoming increasingly important for short-term power-system operation. With increasing renewable generation, demand-side flexibility, and…
arXiv:2512.23964v2 Announce Type: replace-cross
Abstract: Flood models inform strategic disaster management by simulating the spatiotemporal hydrodynamics of flooding. While physics-based numerical flood models are accurate, their substantial computat…
arXiv:2603.13131v3 Announce Type: replace
Abstract: Long-horizon embodied intelligence requires agents to improve through interaction, not merely to execute plans generated from static goals. A central challenge is therefore to transform past executio…