Knowledge catalogue
I tested Mellum2.1-12B-A2.5B (Q8) locally using Pi and llama-server. All five tests were one-shot. Results were pretty mixed: - Pelican SVG, Browser OS, Minecraft: Poor results. - Bouncing Hexagon: Ph
arXiv:2610.10619v1 Announce Type: cross Abstract: Large language model (LLM) agents are rapidly reshaping software engineering, accompanied by an explosion of new code benchmarks. Yet nearly all exist
arXiv:2610.11136v1 Announce Type: new Abstract: Presupposing the boundaries of bias is itself a form of bias. We study closed-loop bias governance for Dutch government documents, where a system must d
The Agent Economy Gala just maxed out at 400 guests Here’s a breakdown: - 203 founders ($1B+ raised combined) - 67 founding operators - 58 investors - 23 creators - 295 guests building agent applicati
arXiv:2610.11744v1 Announce Type: new Abstract: Neural representations can encode more features than they have dimensions, a phenomenon known as superposition. We study the dimension needed to compute
The challenge for Google post-Gemini 4 will be what they do with a good model. Anthropic & OpenAI show we are moving towards a single interface for many tasks with orchestrator agents. The Gemini 3 er
Brenda Goh / Reuters: The Chinese developer of ARTEX says they have converted the AI agent into a closed-source project after CrowdStrike said it was used to hack South Korean banks — The Chinese deve
arXiv:2610.10629v1 Announce Type: new Abstract: Self-improving LLM agents can adapt a credit pipeline to a changed rule, but an agent that rewrites itself destroys the artefact a supervisor reviews: a
arXiv:2406.13267v2 Announce Type: replace Abstract: This paper presents the Kinetics Observer, a novel proprioceptive state estimator for legged robots designed to provide the feedback required for ve
arXiv:2610.11216v1 Announce Type: cross Abstract: Diffusion and autoregression (AR) have long been seen as different categories of generative models, with diffusion specialising in continuous fields a
arXiv:2610.10924v1 Announce Type: cross Abstract: The Tensor-Memory Equilibrium (TME) model of 'FP8 is All You Need (Part 1)' calculates the execution time of Ozaki Scheme II emulation of fp64 as the
arXiv:2610.11504v1 Announce Type: new Abstract: Modern autonomous driving systems rely on bird's-eye-view (BEV) perception models that fuse camera and LiDAR inputs to detect objects in 3D space. These
arXiv:2610.10600v1 Announce Type: cross Abstract: Steinke and Zakynthinou(2020) introduces the Conditional Mutual Information (CMI) framework of analyzing the information complexity of learning algori
arXiv:2610.12004v1 Announce Type: cross Abstract: Understanding how deep neural networks process information remains a central challenge. Existing interpretability methods often compromise structural
The real world abounds with recursively self-improving systems, but one in particular deserves attention: Science, modeled as a system (perhaps even as an agent, with goals and resources). If you want
arXiv:2610.06591v2 Announce Type: replace Abstract: How much of a conference accept/reject decision would change if the same paper were reviewed by a different set of reviewers? Running a second indep
arXiv:2508.19458v2 Announce Type: replace Abstract: A membership-inference attack gets the output of a learning algorithm, and a target individual, and tries to determine whether this individual is a
These days, you can pretty much solve any task by defining an eval and hillclimbing over it, instead of directly defining the deterministic/agentic workflow to solve it. The data provider companies' e
arXiv:2610.11765v1 Announce Type: new Abstract: Large Language Models (LLMs) increasingly ship with explicit 'thinking modes', yet their counterpart, 'no-thinking', has received far less attention. We
Figure 1b from our paper Disclosure: I'm one of the authors (Microsoft). The paper, code, dataset are public and ThinkingBox is on Hugging Face OpenEnv as well. Raw evaluation trajectories are not rel
arXiv:2407.14562v3 Announce Type: replace Abstract: Large language models have demonstrated remarkable capabilities as general-purpose assistants, excelling in a wide range of reasoning tasks and supp
arXiv:2610.11734v1 Announce Type: cross Abstract: We introduce Timer-M1, a pretrained multivariate time series foundation model that learns with primitives for zero-shot forecasting. Across domains, t
arXiv:2610.11105v1 Announce Type: new Abstract: Generating high-quality and controllable camera motion is essential for AI-assisted cinematography, video synthesis, and 3D scene understanding. We intr
The team has announced the launch of **LlamaIndex**, an open‑source information‑retrieval library, with its main site listed at **llamaindex.ai**. The announcement was shared on Twitter by Imaan Sulta
arXiv:2610.11333v1 Announce Type: new Abstract: AI services incur inference costs during execution, while revenue may arrive later. Changing API prices, limited upfront capital, and service failures c
arXiv:2610.12242v1 Announce Type: new Abstract: Large language model (LLM) routing distributes inference work across different models, advancing the cost-quality Pareto frontier of LLM serving. While
arXiv:2610.12428v1 Announce Type: cross Abstract: Building a quantum model involves a tradeoff: how complex the circuit should be, and how much training data it needs. Caro et al. show that models wit
arXiv:2610.12276v1 Announce Type: new Abstract: Legged robots are promising candidates for future lunar surface missions because they can traverse steep, loose, and obstacle-rich terrain that challeng
arXiv:2610.12153v1 Announce Type: new Abstract: We study episodic constrained Markov decision processes with adversarial losses under stochastic hard constraints. Specifically, starting from a known s
arXiv:2610.11072v1 Announce Type: new Abstract: Autonomous navigation in cluttered and constrained environments typically assumes a fixed environment and searches only for paths within existing free s
arXiv:2511.04000v2 Announce Type: replace-cross Abstract: Decision trees are widely used in high-stakes fields like finance and healthcare due to their interpretability. This work introduces an effici
arXiv:2610.11736v1 Announce Type: new Abstract: Modern video generators can realize increasingly complex visual narratives, positioning the prompt enhancer (PE) as a critical bridge from concise user
arXiv:2610.10957v1 Announce Type: cross Abstract: Production AI systems deployed in high-stakes domains accumulate a governance liability that existing monitoring frameworks fail to detect: the progre
arXiv:2610.11678v1 Announce Type: new Abstract: Verifier scores now serve as both benchmark metrics and training rewards for large language model (LLM) agents, and a change in score is routinely read
arXiv:2610.12033v1 Announce Type: cross Abstract: Robotic systems operating over extended tasks must maintain a world state assembled from observations arriving at different times, with varying confid
arXiv:2610.11743v1 Announce Type: new Abstract: We present TraceRelay, an attention-aligned recurrent architecture that distributes persistent representations over a rolling sequence of low-dimensiona
arXiv:2610.11450v1 Announce Type: new Abstract: We study how a coding agent learns across a sequence of abstract reasoning tasks. The agent runs on a frozen foundation model inside a fixed harness and
Training a robot to grasp an object means learning from many attempts, viewpoints and situations. One robot with three cameras at 20 fps produces 216,000 images per hour. Now that robotics is scaling,
arXiv:2610.12232v1 Announce Type: new Abstract: Test-time adaptation (TTA) methods for time-series forecasting update a deployed model, or a small adapter around it, from incoming ground truth. But th
arXiv:2610.11858v1 Announce Type: cross Abstract: Agent skills provide reusable guidance for code agents, but incomplete or unsuitable guidance can impair task execution. To reduce the manual effort o
arXiv:2610.10972v1 Announce Type: new Abstract: Assessing useful reuse in neural PDE solvers is challenging: final accuracy can reflect source learning and target-time computation. Our reuse contract
arXiv:2610.10870v1 Announce Type: cross Abstract: Markov chain Monte Carlo (MCMC) methods are the standard tool for computing expectations under complex probability distributions. Control variates red
arXiv:2610.11037v1 Announce Type: new Abstract: Recent image editing systems have achieved impressive semantic understanding, visual fidelity, and instruction-following ability, while video editing re
arXiv:2604.04246v2 Announce Type: replace-cross Abstract: This paper extends the Transmission Neural Network model proposed by Gao and Caines in [1]-[3] to incorporate inhibitory connections and neuro
TRL v1.15 is out, and it’s an absolute banger of a release for memory-efficient post-training. The main change: SFT, DPO, KTO, GRPO, RLOO and Distillation now use a fused LM head by default. Instead o
arXiv:2601.18751v2 Announce Type: replace-cross Abstract: Preference-based reinforcement learning (PBRL) offers a promising alternative to explicit reward engineering by learning from pairwise traject
Release: ttok 1.0 I released ttok 0.4, ran uv tool upgrade ttok, piped a file into the new version... and realized that it was defaulting to the GPT-4 tokenizer when it should very clearly default to
arXiv:2610.11337v1 Announce Type: cross Abstract: We introduce and study pattern-based tree transformations. As an illustrating example, consider a source pattern (x dot y) + (x dot z) and a target pa
arXiv:2610.11392v1 Announce Type: new Abstract: System One models output calibrated probabilities over typed answers such as categorical choices, ordinal levels, or binary outcomes, via a non-generati
arXiv:2610.11764v1 Announce Type: new Abstract: Reliable crop-row perception is essential for autonomous agricultural robots, but low-cost deployment is constrained by computation, memory, power, and
arXiv:2610.11580v1 Announce Type: new Abstract: Accurate trajectory forecasting and well-defined predictive uncertainty are crucial for reliable, safety-critical applications such as autonomous drivin
arXiv:2610.11737v1 Announce Type: cross Abstract: Bayesian physics-informed neural networks (B-PINNs) are a popular framework for parameter and state inference from sparse or noisy observations. They
arXiv:2610.11866v1 Announce Type: new Abstract: In deep learning, approximation theory motivates increasing representation size. We ask whether this benefit extends to dynamics learning through autore
arXiv:2610.11363v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) are increasingly being applied in a wider range of real-world scenarios. However, due to the substantial labor
arXiv:2610.12172v1 Announce Type: cross Abstract: Learning how actions change scene geometry can provide complementary supervision for goal-directed manipulation. We introduce Spatial Language Modelin
arXiv:2610.12099v1 Announce Type: new Abstract: World action models (WAMs) aim to answer a coupled physical question: given a task instruction, what motion should the robot execute, and how will that
arXiv:2610.12114v1 Announce Type: new Abstract: Knowledge distillation (KD) transfers knowledge from stronger Teacher models to weaker Student models, but most methods require training the Student par
arXiv:2610.12281v1 Announce Type: cross Abstract: Over 90% of disease-associated variants from genome-wide association studies fall in noncoding regulatory regions, yet their functional interpretation
arXiv:2610.11322v1 Announce Type: new Abstract: Geometrically faithful and functional articulated 3D assets are essential for real-to-sim robot manipulation, where policies trained in simulation must
arXiv:2610.12124v1 Announce Type: new Abstract: The evolution of Large Language Model agents from single-task execution to long-term autonomous operation highlights the critical challenge of transform