Deep neural networks extract powerful latent representations from images, enabling fast and efficient downstream analysis. However, these latent spaces lack explicit geometric structure, leading to possibly poor interpolation fidelity and misleading extrapolation. Latent interpolation techniques assume symmetric transi...
Novels tell rich stories, but their textual form cannot directly present the sights and sounds of the worlds they describe. Film adaptations offer an audiovisual experience but require substantial production effort and viewing time; film recaps are shorter but depend on existing footage. Neither route directly provides...
Kyrie You Wu, Chaozhuo Li, Songyang Liu et al.· 0 citations
Heart failure is a serious medical condition associated with risk of acute deterioration, recurrent hospitalizations and high mortality making accurate mortality prediction potentially valuable for patient care and healthcare planning. Numerous prognostic models have been developed using conventional statistics (CS), m...
Erik Aerts, Annika Rosengren, Martin Lindgren et al.· 0 citations
Bitcoin perpetual futures trade continuously with shallow liquidity and high price impact, making them prone to millisecond-scale flash crashes. Agent-based limit order book simulators are a natural tool for studying such events, but their behavioral parameters are usually hand-crafted or require full order book histor...
Inductively Gated Cross-Attention (IGCA), a zero-initialized cross-attention bridge that preserves pretrained model behavior at initialization while enabling gradual multimodal conditioning, is introduced.
Do research agents have taste, the judgment of which experiments are worth running before their outcomes are known? We give six frontier models seven recent NLP papers. Each model, working as a research agent alone or as a team, proposes minimum viable experiments (MVEs), forecasts whether each will pass a threshold it...
Using quarterly FRED and CSO Ireland data over 1995Q1-2025Q4, we examine whether U.S.\ IT investment and Irish data-centre electricity are recomposing the Kitchin cycle around energy- and compute-backed assets. Three findings stand out. First, a Quandt-Andrews sup-Wald test locates a significant break in the U.S.\ IT-G...
Bartosz Ziollko, Adam Niedzialkowski, Bartosz Szyma· 0 citations
Linear activation steering is a powerful approach for controlling and specializing large language models by adding linear representations of concepts to their activations at inference. While effective, existing methods often steer with a fixed strength, independent of how much steering any given input requires. In this...
Brandon Hsu, Daniel Beaglehole, Adityanarayanan Radhakrishnan et al.· 0 citations
This work recast the speculative decoding mechanism from a pure accelerator into an active allocator for context precision that improves the accuracy of long-horizon agents by training 0.06% to 0.28% of hosted parameters.
Hong-Yin Luo, Wei Fang, Lijie Yang et al.· 0 citations
Later tokens are costlier to generate than earlier tokens. On frontier open weight models, the disparity in cost may rise to as much as 7x. Through frequent compaction, we show across a broad range of long-horizon and long-input tasks that frontier language models sacrifice little to no task accuracy when maintaining s...
Peter Belcak, Saurav Muralidharan, Jindong Jiang et al.· 0 citations
Evaluating whether a large language model (LLM) genuinely knows a concept remains a fundamental problem, since behavioral metrics can be fooled by suppression: a model that refuses to answer may still harbor recoverable knowledge. The framework measures the geometric coherence of \textit{anon-vectors}, the differences...
Adar Peleg, Dvir Alsheich, Tomer Ashuach et al.· Conference on Empirical Meth...· 0 citations
Multimodal web agents have shown promising capabilities for interacting with websites through graphical user interfaces (GUIs), yet realistic web tasks often require long-horizon, multi-step planning that remains challenging for monolithic policies. Such agents must jointly infer high-level plans, navigate through inte...
