Claims Browser

Latent chain-of-thought models improve compactness by moving intermediate reasoning from emitted text into continuous states, but this hides the causal object.

"Latent chain-of-thought models move intermediate reasoning from emitted text into continuous states, improving compactness but hiding the causal object."

SCIT (Suffix Cache Interchange Test) can identify which transformer object carries counterfactual computation through causal protocols that construct exact source-recipient counterfactuals and patch cache segments.

"We introduce SCIT, the Suffix Cache Interchange Test, a causal protocol that constructs exact source-recipient counterfactuals, patches declared cache segments, and identifies which transformer object carries the counterfactual computation."

In CODI-GPT2 and Sim-CoT-style GPT-2 models, counterfactual arithmetic transfers primarily through value-cache suffix trajectories rather than through hidden states, keys, reusable answer slots, or single-token triggers.

"On CODI-GPT2 and a Sim-CoT-style GPT-2 reproduction, counterfactual arithmetic transfers primarily through value-cache suffix trajectories rather than hidden states, keys, reusable answer slots, or single-token triggers."

SCIT reveals carrier-regime shifts where arithmetic-like GPT-2/1B cells preserve latent-tail value/KV transfer, while competent 8B and repaired non-arithmetic cells route through prompt-prefix or full-cache K/V instead.

"SCIT reveals carrier-regime shifts: arithmetic-like GPT-2/1B cells preserve latent-tail value/KV transfer, whereas competent 8B and repaired non-arithmetic cells route through prompt-prefix or full-cache K/V"

SCIT contributes a cache-level diagnostic and a competence-gated carrier map rather than a universal latent-tail claim, showing that mechanism behavior is checkpoint-specific.

"SCIT therefore contributes a cache-level diagnostic, a checkpoint-specific GPT-2 arithmetic mechanism, and a competence-gated carrier map rather than a universal latent-tail claim."

Vision generative AI has emerged as one of the most rapidly advancing areas of deep learning

"Vision generative artificial intelligence (AI) has emerged as one of the most rapidly advancing areas of deep learning."

PDPO (Planning Diffusion Policy Optimization) achieves an improved success rate over strong baselines in crowd navigation tasks

"Experiments show that PDPO obtains an improved success rate over strong baselines"

Prediction of Prediction (PoP) achieves 75.5% AUROC for factual-correctness classification on TruthfulQA

"PoP achieves an area under the receiver operating characteristic curve (AUROC) of 75.5% for factual-correctness classification"

Frontier AI model performance is achievable by a wide range of institutions through continual learning on open-weight models, at substantially lower compute and personnel budgets than commonly thought

"frontier performance is achievable by a wide range of institutions through Continual Learning on readily available open-weight models"

The continual learning approach yields gains comparable to those typically seen across multiple successive model generations

"This yields gains comparable to those typically seen across multiple successive model generations, at compute and personnel budgets substantially lower than commonly thought"

Thomson model performs competitively with recent frontier models across agentic tasks, safety, legal, tax, multilingualism, and large-scale Deep Research

"Thomson performs competitively with recent frontier models across agentic tasks, safety, legal, tax & multilingualism, and large-scale Deep Research"

The approach almost completely eliminates the forgetting problem common to narrow domain adaptation while improving capabilities across a wide range

"distinct improvements across a wide range of capabilities, including those not explicitly targeted, while almost completely eliminating the forgetting problem common to narrow domain adaptation"

Development of frontier models is commonly perceived to be exclusive to a small number of heavily funded players, creating information, economic and power asymmetry

"The development of frontier models is commonly perceived to be the exclusive remit of a small number of heavily funded players, creating an information, economic and power asymmetry between developers and the diverse user base of modern AI"

Ownership of large parts of the SovereignAI stack (model, tool infrastructure, values, and data privacy) is viable for far more actors through this continual learning approach

"making ownership of large parts of the SovereignAI stack (model, tool infrastructure, values & data privacy) viable for far more actors"

Conversational AI systems such as chatbots and virtual assistants are becoming increasingly important to digital business processes

"Conversational AI systems, such as chatbots and virtual assistants, are becoming increasingly important to digital business processes."

The established BPMN standard faces challenges when representing dynamic, context-sensitive interactions in conversational AI

"the established Business Process Model and Notation (BPMN) standard faces challenges when representing dynamic, context-sensitive interactions"

The BPMN4CAI extension facilitates adaptive decision-making processes, robust context management, and transparent interactions for Conversational AI within business processes

"The results show that the BPMN4CAI extension facilitates adaptive decision-making processes, robust context management, and transparent interactions for Conversational AI within business processes."

Event-based object classification using Spiking Neural Networks on neuromorphic devices can solve issues of size, weight, power consumption, security, latency, and connectivity present in conventional frame-based computer vision approaches

"The use of Spiking Neural Networks (SNNs) hosted on neuromorphic devices attempts to solve several issues present in this conventional approach."