AI Intelligence Archive

When AI agents act on behalf of users, traditional audit logs often don't tell the full story of who...

Hello, I'm Maneshwar, and I'm building LiveReview — a blast-radius aware AI code review built for...

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass ...

Language models increasingly support or automate information retrieval from document collections too large to index. This task is difficult when it requires specialist linguistic or scientific knowledge. We used the Wikipedia Game to test …

Interpreting machine learning model predictions is a central challenge, particularly for black-box vision models. Concept-based attribution methods interpret models using human-understandable concepts. Existing concept-based methods can on…

Hello, I'm Rijul, and I'm building LiveReview — a blast-radius aware AI code review built for your...

The expressivity of a neural network $Φ$ describes the class of functions that a network can express. The term topological expressivity refers to a family of measures particularly suited to understand binary classification and is often for…

Capability evaluations aim to surface dangerous model behaviors before deployment, but their reliability depends on the assumption that hidden capabilities can be elicited. We show this assumption does not hold under adversarial conditions…

This is a submission for the Kaggle Benchmarking Challenge. This would probably needs its own...

A parallel sampler can choose at random which coordinates to generate together. For a target $p$ and the output law $q_U$ of a schedule $U$ drawn afresh for each output, we compare the schedule-averaged divergence $\mathbb{E}_U D_{\mathrm{…

Deep-space communications operate under intermittent connectivity, long propagation delays, and relay storage constraints. In such networks, the Bundle Protocol enables store-carry-forward communication, requiring relay nodes to manage lim…

Clinical sleep medicine repeatedly documents profound divergences between objective sleep duration and subjective daytime impairment, notably exemplified by sleep state misperception in paradoxical insomnia and boundary instability in narc…

A central challenge in de novo protein design is generating proteins with desired structural and functional properties. Existing design models typically require a dedicated input representation for each property, limiting the design object…

Qwen3.8-27B, 600 steps, 12 reward channels: CISPO, REPO-R and prompt filtering lifted holdout from −0.47 to +1.80, and an advantage floor silently zeroed 96% of the signal.

Recursive self-improvement (RSI) aims to transform interaction experience into persistent improvements, yet external feedback is costly and world-model predictions may become unreliable as policies evolve. We introduce RSI-Anything, a doma…

Vision-Language Models (VLMs) increasingly analyze and reason about images, yet it remains unclear whether their internal representations faithfully encode the structured relations required for such reasoning. We introduce EICS (Evaluation…

While deep learning models for tabular data have recently received significant research attention, the choice of objective functions for regression tasks remains an understudied degree of freedom. Several lines of research offer alternativ…

We study the last iterate of standard asynchronous Q-learning from a single trajectory of a finite Markov decision process. The trajectory follows a fixed behavior policy whose state--action chain is irreducible and may be periodic. For di…

Neural semantic parsers generate meaning representations token by token, yet well-formedness depends on references, scope, and graph relations that unfold during generation. Constrained decoding prevents locally invalid tokens but does not…

Large language models reuse the same attention heads across tasks, but identifying these shared heads does not explain what they do differently in each task. A natural source of inspiration is task-dependent interactions among shared brain…

A concrete example connecting slot_mapping, block_table, cache layouts, and tiled attention.

As AI agents increasingly rely on external tools, accurate retrieval is essential for reliable behavior. Existing methods optimize semantic relevance but largely ignore tool availability during execution. To address this gap, we propose RA…

Personal agents increasingly connect to services across the web and applications by using tools. As the effects of their actions accumulate and interact across services, unintended or harmful outcomes can arise when agents fulfill benign u…

A memory that reproduces every current prediction may still have forgotten how to learn from the next observation. We characterize this distinction for exact cumulative learning and attention. For smooth convex residual losses with unrestr…

This is a submission for the Kaggle Benchmarking Challenge TL;DR I asked 6 vision models to...

Many optimization problems provide direct access to only part of the gradient, while the remaining component must be inferred from function evaluations. This structure arises in performative prediction, performative reinforcement learning,…

Google AI Overviews appeared on a far larger share of tracked branded searches during September 2026,...

Another Rule for Using AI Without Losing My Skills ...

We establish finite-sample guarantees for conditional diffusion models learned from data and implemented with finitely many denoising steps. Our approach aligns the score-training objective with the sampling grid, allowing statistical esti…

Generative molecular design typically relies on over-generation and post-hoc filtering. Inference-time steering methods like Feynman-Kac (FK) steering improve efficiency by biasing trajectories toward high-reward candidates, yet they optim…

Time-aware facts, an entity graph measured honestly, and three bugs I only found because strangers read my posts.

This is a submission for the Kaggle Benchmarking Challenge Last weekend I built a model to predict...

n8n appears to be exploring how end-to-end automation could reduce repetitive design work, but it has...

Routing 5% of hard tokens to a 32B model and keeping the rest on a 0.6B model looks great on paper, until standard serving engines spend 95.8% of the step redoing prefix matching. TokenRouter fixes the scheduler and hits up to 64x higher t…

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass ...

Independent review. I ran both tools on my own accounts, free and paid, with no vendor-provided access or early access of any\u00a0kind.

Every time a RAG application answers a question, it may need to retrieve documents and make an LLM...

This is a submission for the Kaggle Benchmarking Challenge. I Benchmarked 3 LLMs on...

https://www.kaggle.com/competitions/arc-prize-2026-arc-agi-2/leaderboard

https://www.kaggle.com/competitions/arc-prize-2026-arc-agi-3/leaderboard