arXiv:2605.08167v1 Announce Type: cross
Abstract: The increasing availability of advanced image editing tools has led to a significant rise in manipulated digital content, posing serious challenges for digital forensics and information security. This …
arXiv:2605.08144v1 Announce Type: cross
Abstract: Diffusion models have achieved remarkable success across a wide range of generative tasks, yet their training paradigm largely treats injected noise as uniformly informative. In this work, we challenge…
arXiv:2605.08665v1 Announce Type: new
Abstract: Large reasoning models achieve high accuracy through extended chain-of-thought but generate 5–8 more tokens than necessary, applying verbose reasoning uniformly regardless of problem difficulty. We prop…
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:2605.08729v1 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:2605.08174v1 Announce Type: cross
Abstract: To mitigate the memory constraints associated with fine-tuning large pre-trained models, existing parameter-efficient fine-tuning (PEFT) methods, such as LoRA, rely on low-rank updates. However, such u…
arXiv:2605.08344v1 Announce Type: new
Abstract: Recent work has shown that models flow matching models can be trained without explicit time conditioning, challenging the standard view that the interpolation time is needed to disambiguate velocity targ…