· ai
[Paper] Relational Visual Similarity
Humans do not just see attribute similarity -- we also see relational similarity. An apple is like a peach because both are reddish fruit, but the Earth is also...
-
- · ai
[Paper] Do Generalisation Results Generalise?
A large language model's (LLM's) out-of-distribution (OOD) generalisation ability is crucial to its deployment. Previous work assessing LLMs' generalisation per...
- · ai
[Paper] One Layer Is Enough: Adapting Pretrained Visual Encoders for Image Generation
Visual generative models (e.g., diffusion models) typically operate in compressed latent spaces to balance training efficiency and sample quality. In parallel, ...
- · ai
[Paper] The Adoption and Usage of AI Agents: Early Evidence from Perplexity
This paper presents the first large-scale field study of the adoption, usage intensity, and use cases of general-purpose AI agents operating in open-world web e...
- · ai
[Paper] An Adaptive Multi-Layered Honeynet Architecture for Threat Behavior Analysis via Deep Learning
The escalating sophistication and variety of cyber threats have rendered static honeypots inadequate, necessitating adaptive, intelligence-driven deception. In ...
- · ai
[Paper] WorldReel: 4D Video Generation with Consistent Geometry and Motion Modeling
Recent video generators achieve striking photorealism, yet remain fundamentally inconsistent in 3D. We present WorldReel, a 4D video generator that is natively ...
- · ai
[Paper] Graph-Based Learning of Spectro-Topographical EEG Representations with Gradient Alignment for Brain-Computer Interfaces
We present a novel graph-based learning of EEG representations with gradient alignment (GEEGA) that leverages multi-domain information to learn EEG representati...
- · ai
[Paper] Provable Long-Range Benefits of Next-Token Prediction
Why do modern language models, trained to do well on next-word prediction, appear to generate coherent documents and capture long-range structure? Here we show ...
- · ai
[Paper] Understanding Privacy Risks in Code Models Through Training Dynamics: A Causal Approach
Large language models for code (LLM4Code) have greatly improved developer productivity but also raise privacy concerns due to their reliance on open-source repo...
- · ai
[Paper] Auditing Games for Sandbagging
Future AI systems could conceal their capabilities ('sandbagging') during evaluations, potentially misleading developers and auditors. We stress-tested sandbagg...
- · ai
[Paper] LUNA: LUT-Based Neural Architecture for Fast and Low-Cost Qubit Readout
Qubit readout is a critical operation in quantum computing systems, which maps the analog response of qubits into discrete classical states. Deep neural network...
- · ai
[Paper] Group Representational Position Encoding
We present GRAPE (Group RepresentAtional Position Encoding), a unified framework for positional encoding based on group actions. GRAPE brings together two famil...