arXiv:2604.07904v2 Announce Type: replace-cross Abstract: Spatiotemporal neural dynamics and oscillatory synchronization are widely implicated in biological information processing and have been hypothesized to support flexible coordination…
arXiv:2606.25745v1 Announce Type: new Abstract: Mean Field Variational Inference (MFVI) is widely understood to underestimate posterior variance. By analysing conjugate Bayesian Linear Regression (BLR), we show…
arXiv:2606.24973v1 Announce Type: new Abstract: We introduce a dataset of 32,534 double-marked real student responses to GCSE mock exams (GCSEs are the UK's national exams, taken…
arXiv:2606.25975v1 Announce Type: cross Abstract: Common first-order optimizers, such as Adam, implicitly treat each parameter block as an unstructured vector, which disregards the multilinear weight structure…
arXiv:2601.17037v2 Announce Type: replace Abstract: We investigate visual reasoning limitations of both multimodal large language models (MLLMs) and image generation models (IGMs) by creating a novel…
arXiv:2606.24945v1 Announce Type: new Abstract: We ask a representation-learning question about physical world models: when does a conservation law remain certifiable after a model learns a…
arXiv:2606.24949v1 Announce Type: cross Abstract: This work investigates the interpretability of a Wav2Vec 2.0based speech intelligibility assessment model for oral and oropharyngeal cancer patients through canonical…
arXiv:2606.25601v1 Announce Type: new Abstract: Hyperparameter selection is a critical step in the deployment of modern artificial intelligence systems, given the need to tune degrees of…
arXiv:2606.24952v1 Announce Type: new Abstract: A central aspiration of mechanistic interpretability is controllability: if we know where a behavior is represented in a model's activations, we…
arXiv:2606.24570v2 Announce Type: replace Abstract: Vision-language contrastive pretraining has become the dominant recipe for 3D medical foundation models, leveraging the large volumes of paired scans and…
arXiv:2606.25220v1 Announce Type: new Abstract: Real-time texture transfer expands the creative horizon for interactive applications, enabling seamless detail projection in scenarios that range from digital character…
arXiv:2606.24946v1 Announce Type: new Abstract: Learned world models are useful only over horizons on which their rollout error remains controlled. We study trust-horizon certification for latent…
Chain-of-Thought (CoT) has become a standard method for improving reasoning capabilities in large language models (LLMs) by eliciting step-by-step thinking, but its effectiveness in multimodal tasks…
We introduce Autodata, a general method that enables AI agents to act as data scientists who build high quality training and evaluation data. We show how…
Open domain subject-driven text-to-video (S2V) generation has drawn significant interest in academia and industry. Open domain S2V mainly involves two scenarios: in-domain, which requires retaining the…
The Hitchhiker's Guide to Agentic AI is a comprehensive practitioner's reference for building autonomous AI systems. The book covers the full stack from first principles to…
Existing low-bit KV-cache quantizers often treat each cached key as a flat vector. Under RoPE, however, a key's contribution to a future attention logit decomposes into…
Modern large language models are predominantly trained with autoregressive factorization and causal attention. We present iLLaDA, an 8B masked diffusion language model trained from scratch with…
Autoregressive video diffusion with causal diffusion transformers has emerged as a major paradigm for real-time streaming video generation and action-conditioned interactive world models. In this work,…
While Large Language Models (LLMs) have substantially advanced text-to-code synthesis, many real programming tasks specify intent through visual artifacts such as screenshots, charts, vector drawings, videos,…
Unified multi-modal large language models (MLLMs) have achieved strong text-to-image generation quality, but still struggle with structure-aware prompt following, where object counts, spatial relations, attribute bindings,…
WordArt (artistic text) features highly customized fonts, textures, and layouts, making WordArt-oriented scene TExt Recognition (WATER) substantially more challenging than general Scene Text Recognition (STR). Existing…
We present Wan-Streamer, a native-streaming, end-to-end interactive foundation model designed from the ground up for real-time, low-latency, full-duplex audio-visual interaction. Wan-Streamer seamlessly models language, audio, and…
Long-term memory promises LLM agents that grow more capable across sessions, maintaining an accurate, evolving understanding of the user that interaction forms. In practice, however, this…