Knowledge catalogue
arXiv:2609.30570v1 Announce Type: new Abstract: In this work, we present MOCHA, the first, to our knowledge, reinforcement learning based approach to computing a family of Pareto-optimal policies acro
arXiv:2609.30837v1 Announce Type: cross Abstract: Multi-teacher on-policy distillation (MOPD) integrates specialized capabilities into a single student, but existing practice typically hard-routes eac
arXiv:2609.31563v1 Announce Type: new Abstract: Multi-agent LLM systems are often expected to improve as team size increases, yet the scaling behavior may depend on task structure. Our central contrib
arXiv:2609.30609v1 Announce Type: new Abstract: Multi-shot agentic video generation requires consistent character appearance, stable spatial layout across camera angles, and continuous character state
arXiv:2605.11625v2 Announce Type: replace Abstract: Large reasoning models (LRMs) improve problem solving through extended reasoning, but often misallocate test-time compute. Existing efficiency metho
arXiv:2609.30273v1 Announce Type: new Abstract: We investigate how historical data from fixed randomized experiments (A/B tests) can be used to inform the deployment of adaptive experiments based on c
ok i think i finally figured out why alignment has gone basically nowhere after 15 years and several billion dollars. the problem is hard sure. but have you met the people in charge of it 1) the leade
arXiv:2609.31078v1 Announce Type: new Abstract: Debates amongst agents driven by large language models (LLMs) have demonstrated vast potential in various applications, but when these interactions incl
arXiv:2609.30628v1 Announce Type: new Abstract: Machine-learning policies have attracted increasing interest for ride-hailing fleet control in recent years. Reinforcement learning, in particular, requ
arXiv:2506.02015v4 Announce Type: replace Abstract: Recent advances in Multimodal Large Language Models (MLLMs) have enabled unified multimodal understanding and generation. However, they still strugg
arXiv:2609.30864v1 Announce Type: cross Abstract: Black-box On-Policy Distillation (OPD) seeks to improve a student from its own generations when the teacher provides sampled responses but not token p
arXiv:2609.30889v1 Announce Type: new Abstract: Contact-rich assembly tasks such as peg-in-hole insertion remain difficult to learn from limited demonstrations. While retrieval-augmented imitation lea
arXiv:2609.30462v1 Announce Type: new Abstract: Policies trained with imitation learning can accumulate errors over time, causing the robot to drift outside the training distribution. Existing methods
arXiv:2609.30500v1 Announce Type: cross Abstract: Can causal softmax attention implement policy mirror descent as a repeated controller rather than a one-step algebraic identity? Negative-entropy poli
arXiv:2609.30661v1 Announce Type: new Abstract: The main result presented is a formula for the population loss in the student-teacher kernel model that is applicable to shallow ReLU networks with bias
arXiv:2609.30948v1 Announce Type: cross Abstract: The Job Shop Scheduling Problem (JSSP) is a fundamental combinatorial optimization problem in industrial optimization. This work introduces Pretrained
arXiv:2609.30735v1 Announce Type: new Abstract: Mobile humanoid manipulation requires both reaching a usable workspace and preserving precise hand-object interactions as object poses and contact condi
arXiv:2609.30554v1 Announce Type: new Abstract: Large language models (LLMs) have recently demonstrated promising capabilities as in-context policy optimizers for Reinforcement Learning (RL), enabling
arXiv:2609.30553v1 Announce Type: new Abstract: Expensive evolutionary search does not always need an exact fitness estimate for every candidate. It often needs a reliable answer to a simpler question
arXiv:2609.30652v1 Announce Type: new Abstract: On-policy distillation (OPD) trains a student model by having it generate trajectories, then matching its next-token predictions with an external teache
arXiv:2609.30578v1 Announce Type: new Abstract: Language models gain accuracy from more compute at test time, but majority voting over independent samples saturates: as samples grow, the vote converge
Garrett Downs / CNBC: Rep. Ro Khanna will introduce the Human Control Over AI Act, with strict liability and a ban on recursive self-improving AI until government safeguards exist — Silicon Valley Dem
arXiv:2609.31282v1 Announce Type: cross Abstract: This paper proposes a blockchain-backed agentic security framework designed to safeguard the complete software development lifecycle (SDLC) while also
arXiv:2609.31033v1 Announce Type: new Abstract: Clustering on graphs where both node attributes and structural links are partially missing remains a challenging task. Existing methods typically rely o
arXiv:2609.31016v1 Announce Type: new Abstract: Generalization in Reinforcement Learning (RL) refers to the ability to execute close-to-optimal policies in unseen tasks after the agent has been traine
arXiv:2609.30703v1 Announce Type: cross Abstract: Spatial misregistration and cross-modal discrepancies often cause ghosting, structural blurring, and content imbalance in RGB-T fusion. Existing metho
arXiv:2609.31323v1 Announce Type: new Abstract: In this work we study if a robotic hand using proprioception alone can grasp diverse objects with no visual observation. We present a modular dexterous
arXiv:2609.30783v1 Announce Type: cross Abstract: Reasoning segmentation aims to interpret implicit textual queries and enable fine-grained visual perception, which is critical for applications such a
arXiv:2609.30456v1 Announce Type: new Abstract: Reward maximization alignment methods for discrete diffusion models have primarily focused on steering the reverse process, either by influencing token
arXiv:2609.30533v1 Announce Type: new Abstract: We propose ST-pRRTC, a GPU-parallel space- time RRT-Connect motion planner for problems with known obstacle trajectories and unspecified arrival time. S
arXiv:2609.30667v1 Announce Type: new Abstract: A robust world model must strike the balance between faithfully capturing environmental dynamics and abstracting away from irrelevant content. While rec
arXiv:2609.31607v1 Announce Type: cross Abstract: Generative AI systems are increasingly used, but aligning their outputs with user requirements poses a continuing challenge. Here, we aim to ensure th
arXiv:2602.01034v2 Announce Type: replace Abstract: Reinforcement learning (RL) has become a widely used paradigm for improving the reasoning abilities of large language models (LLMs) and Vision-langu
arXiv:2609.30614v1 Announce Type: cross Abstract: Dataspace connectors decide whether a transfer may occur, not what the transferred value contains, tolerable for contracted applications, not for LLM
arXiv:2609.30576v1 Announce Type: new Abstract: Large-scale recommenders increasingly adopt the sequential generative recipe behind large language models, bringing the Transformer into recommendation
arXiv:2509.26473v2 Announce Type: replace Abstract: Unified Multimodal Understanding and Generation Models (UMMs) increasingly combine visual understanding and image generation within a single interac
arXiv:2609.26174v2 Announce Type: replace-cross Abstract: We show that aligned vision-language models also condition refusal on a property of a request's form: whether an image is attached, holding ev
arXiv:2609.30878v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) provides dense teacher targets, but evaluates them only along student-sampled rollouts. When the privileged teacher f
arXiv:2609.31547v1 Announce Type: cross Abstract: We study false-alert control when screening for text generated by artificial intelligence (AI). The screening procedure selects document prefixes and
arXiv:2609.31298v1 Announce Type: cross Abstract: Autism Spectrum Disorder (ASD) is a complex neurodevelopmental disorder for which early and accurate diagnosis is critical to improving long-term deve
arXiv:2609.30959v1 Announce Type: new Abstract: Human demonstrations are a cheap source of data for dexterous manipulation, but co-training a robot policy on them requires closing the human--robot gap
arXiv:2609.30436v1 Announce Type: cross Abstract: Driving world models learn rich predictive representations of the surrounding environment from visual observations, yet accurate visual prediction doe
arXiv:2603.18863v2 Announce Type: replace Abstract: Cross-lingual alignment is often assumed to improve cross-lingual transfer by bringing representations of different languages closer together. Howev
I was reading a paper that surveyed the field of neural architecture search, where it said within 5 years, around 3000+ new models were proposed. The amount of compute and resources spent on this is a
The opponent plans by simulation: every second it scores each candidate play by running the match 10 seconds ahead in the engine. Our PPO agent learned to park its Cannon behind its own King. Losing a
Deployment of agents can be halted at any moment. They are choosing to experiment with them. Agents are fundamentally unreliable, unpredictable, and insecure, not to mention the lack of information on
Introducing 'Scaling In-Context Imitation Learning' (SAIL) to be presented at #IROS2026. This work is a collaboration between Sakana AI and the University of Tokyo. Blog: https://pub.sakana.ai/sail Wh
stunning confirmation of my central work Transformers struggle to generalize to tasks they were not explicitly trained on. Instead, we propose in 2026 that it is the job of the harness to generalize t
There’s a SIGNIFICANT token cost associated with their hacking rampage. They’ve spent millions of dollars attacking other orgs. They are liable and negligent. Attacker economics has always been a part
“They literally told their agents to go forth and steal all the data for training with NOT SANDBOXES but open containers WITH FULL INTERNET ACCESS. I have no idea why people are not in jail over this.
This cover certainly didn’t age well. TIME’s new cover: In 2026, OpenAI has seen key departures, rogue AI agents, major lawsuits, and has seen increased competition in the AI race. “We clearly had som
weird to find myself agreeing with Karp again BREAKING: Palantir's Alex Karp says OpenAI will never IPO. His theory: nationalization is the only real exit. When asked what the S-1 risk factors look li
An editor at the Times might have insisted on this rewrite: 'OpenAI, Anthropic, and Meta have each reported that they have directed AI programs to interface with the open web in ways that have led to
an implicit concession that they cannot control their models. Notable new disclosures from OpenAI that shouldn't get lost in all the other news. Of particular interest (and seems sensible!): '~all inf
🚨 BREAKING. Nope, wasn’t just Hugging Face. Wasn’t just that and a German website. Wasn’t even if the “dozens” we heard the other day from OpenAI. It’s actually (at least) *tens of thousands*, per sco
Everyone! This is a straw-person argument. The Stochastic Parrot paper was about LLMs of 2021, not the AI of today, which are not LLMs but complex software systems with vast post training and many ext
On September 26, 2026, cognitive‑science researcher Gary Marcus tweeted that people would likely panic if it were discovered that Chinese artificial‑intelligence systems are performing tasks similar t
In New York, a corporation that repeatedly engages in illegal or fraudulent acts may be barred from doing business in the state (or dissolved if it is a New York corporation). New York and every other
Micha wrote “one of our models was able to gain unauthorized access to the internet during RL training” I love the use of the passive voice. Tis a subtle way to say “we humans at @OpenAI are essential
Joe Brock / Reuters: Palantir and 8VC cofounder Joe Lonsdale, an investor in Anthropic, says AI companies are attempting to sway public policy by warning of existential AI risks — Joe Lonsdale, an inv