All entries

arXiv:2609.00003v1 Announce Type: new Abstract: Machine unlearning studies the removal of knowledge from an AI model, making the system forget a concept it previously learned. Despite rapid progress i

I highly encourage anyone interested in AI safety to read this. I remember discussing the importance of observability with my mates at @BlueDotImpact last year. This feels more important than ever URG

I see a lot of my TL freaking out about this Here is the reality: Frontier models will one shot just about anything at 10,000 tokens per second in a few years Do you really think we can monitor that?

I want to prevent a race into unmonitorability kicked off by confused reporting. The depth of the computation graph for our present frontier models, including Astra, is within a factor of two of GPT-4

arXiv:2512.05539v3 Announce Type: replace Abstract: The visible parts of a scene are determined by occlusion among overlapping surfaces. Here we consider 'dead leaves' models, which replicate this by

If this is true, OpenAI seems to be violating one of the few redlines that exist in the AI industry. Absolutely do not train your models like this - what is going on?? Really huge and extremely concer

I've said this in another post, but again started with Claude Code, loved OpenCode, but I felt chained and tied to them both for the longest time (especially CC, just the worst). I felt less productiv

arXiv:2609.00161v1 Announce Type: new Abstract: World models have made remarkable progress in action-conditioned future prediction for embodied agents, yet still struggle to model physically plausible

arXiv:2609.00563v1 Announce Type: cross Abstract: Animals and robots encounter mud at the water-land interface. Like sand, mud can stay solid or flow like a fluid. Unlike sand, the yield strength of m

In case you're wondering while this steaming POS is being floated now, it's because SoftBank needs to refinance the 40B bridge loan it used to invest 30B into OpenAI before it matures in March 2027...

arXiv:2609.00904v1 Announce Type: new Abstract: Whether large language models (LLMs) can control their own internal representations matters for both machine metacognition and AI safety. A recent study

in other words, generative AI is poised to become a complete clusterfuck. All three pillars of a safety case look about to fall. We are rather likely to have highly capable, poorly monitorable, dubiou

arXiv:2505.22156v4 Announce Type: replace Abstract: Although existing model editing methods perform well in recalling exact edit facts, they often struggle in complex scenarios that require deeper sem

arXiv:2609.00005v1 Announce Type: new Abstract: Financial scams targeting older adults increasingly occur through text and voice channels such as email, SMS, and phone calls, unfolding over multiple c

arXiv:2609.00504v1 Announce Type: cross Abstract: In this work, we study radically uncoupled learning in discounted general-sum Markov games. Assuming ``mathsf{ETH} for mathsf{PPAD}', we show that, fo

Independent verifiers improve agent output - but frontier verifiers are expensive. So we trained our own. Results on @GoogleDeepMind's FACTS-Search: > No verifier: 89.4 (previously published SOTA) > W

arXiv:2511.09454v2 Announce Type: replace-cross Abstract: As algorithms increasingly mediate competitive decision-making, their influence extends beyond individual outcomes to shaping strategic market

arXiv:2609.01383v1 Announce Type: new Abstract: Vision Language Models have demonstrated remarkable proficiency in interpreting static visual artifacts, but modern data analysis is inherently dynamic,

arXiv:2609.00998v1 Announce Type: cross Abstract: Word Sense Disambiguation has advanced rapidly for English and a handful of well-resourced modern languages, but it continues to assume the existence

arXiv:2609.00447v1 Announce Type: new Abstract: Accurate 3D abnormality segmentation in chest CT requires dense spatial supervision, but obtaining expert voxel-level labels is costly. Radiology report

arXiv:2609.00791v1 Announce Type: cross Abstract: In this work, we introduce Instella-MoE, a fully open Mixture-of-Experts (MoE) language model with 16 billion total parameters and 2.8 billion active

arXiv:2609.01339v1 Announce Type: new Abstract: Road traffic noise remains a major environmental challenge, yet most speed management strategies are static and do not respond to short-term variations

arXiv:2609.00181v1 Announce Type: cross Abstract: The number of edge devices in large-scale edge systems is rapidly increasing. Edge devices have limited processing power, memory, and network bandwidt

arXiv:2608.29632v1 Announce Type: cross Abstract: Competitive programming is increasingly being used to evaluate the algorithmic reasoning capabilities of large language models (LLMs). However, existi

arXiv:2609.01375v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) have achieved strong multimodal performance, yet ensuring the factual correctness of generated content remains ch

Introducing Gemini 3.8 Flash, another jump in Gemini's agentic + coding capabilities, and our 3rd updated Flash model in only 6 weeks... This model has been a ton of fun to work with, excited to see w

arXiv:2609.00243v1 Announce Type: new Abstract: LLM agents that cache recovery suggestions from API errors can skip re-derivation in later episodes, spending fewer tokens and fewer model calls on cons

arXiv:2609.00311v1 Announce Type: new Abstract: The inverse kinematics of generic 3R robots has been investigated through multiple approaches, mainly algebraic methods involving the solution of certai

arXiv:2603.03229v3 Announce Type: replace Abstract: The shock response spectrum (SRS) is widely used to characterize the response of single-degree-of-freedom (SDOF) systems to transient accelerations.

arXiv:2609.00625v1 Announce Type: cross Abstract: Faithfully capturing diverse real-world objects with fuzzy, anisotropic structures, such as hair, fur, fibers, and textiles, for efficient real-time v

arXiv:2609.00608v1 Announce Type: new Abstract: LLM-based user simulators are increasingly used to evaluate autonomous agents at scale, in place of costly human evaluations. Despite this promise, thes

arXiv:2609.00449v1 Announce Type: cross Abstract: Neuroevolution of Augmenting Topologies (NEAT) and its advanced version, Evolvable-Substrate HyperNEAT (ES-HyperNEAT), have shown great potential in d

arXiv:2609.01361v1 Announce Type: new Abstract: Linear classifiers trained on hidden states of a large language model (LLM), linear probes, can flag factual errors from a single forward pass. Geometri

arXiv:2609.00883v1 Announce Type: new Abstract: Phase retrieval in broadband coherent anti-Stokes Raman spectroscopy (BCARS) is an ill-posed inverse problem. The Raman-like signal is encoded in the im

arXiv:2602.09691v2 Announce Type: replace Abstract: Knowledge distillation (KD) is a technique to compress a larger teacher system into a smaller student. In machine translation, KD is commonly evalua

arXiv:2609.00513v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) mitigates large language models (LLMs) hallucinations, yet conventional dense retrieval struggles with the complex

arXiv:2609.00638v1 Announce Type: cross Abstract: Retrieval is the first stage of modern search and advertising systems, selecting a candidate set from a large item universe for downstream ranking and

arXiv:2609.01092v1 Announce Type: new Abstract: Text-guided image fusion has recently emerged as an effective paradigm for integrating multi-modal information while enabling flexible and task-oriented

arXiv:2511.21638v2 Announce Type: replace Abstract: Practical LLM agents often operate over multi-turn conversations where success is determined only after the full interaction ends. Most multi-turn R

arXiv:2609.01168v1 Announce Type: new Abstract: Text-to-image (T2I) models remain vulnerable to jailbreak attacks that elicit Not-Safe-For-Work (NSFW) content, despite increasingly being guarded by he

arXiv:2606.20563v2 Announce Type: replace Abstract: Creating 3D visual illusions, a single 3D mesh that reveals entirely different semantics from various viewing angles, is a fascinating but tough cha

arXiv:2609.00756v1 Announce Type: new Abstract: The Mutual Reinforcement Effect (MRE) asks whether a fine, span-level and a coarse, document-level task help each other when one model handles both. We

arXiv:2408.12845v3 Announce Type: replace-cross Abstract: This paper considers a novel variant of the online fair division problem involving multiple agents in which a learner sequentially observes an

arXiv:2511.04093v2 Announce Type: replace Abstract: Large language models (LLMs) excel at reasoning but struggle with knowledge-intensive questions due to limited context and parametric knowledge. How

arXiv:2609.00082v1 Announce Type: cross Abstract: LLMs acquire vast amounts of knowledge during pre-training, but often lack the specialized knowledge needed to answer questions from niche sources suc

arXiv:2609.00908v1 Announce Type: new Abstract: Action chunking is a standard execution strategy in modern Vision-Language-Action (VLA) frameworks, but fixed execution horizons impose a trade-off betw