Knowledge catalogue
arXiv:2410.01917v3 Announce Type: replace-cross Abstract: Originally introduced in game theory, Shapley values have emerged as a central tool in explainable machine learning, where they are used to at
arXiv:2610.13008v1 Announce Type: new Abstract: In repeated human-AI interaction, a single observation can be quoted, summarized, and returned to a model as multiple reports, making repetition look li
arXiv:2610.12766v1 Announce Type: new Abstract: Machine-learning models for perovskite solar cells are typically evaluated using random data splits, which we show systematically leak information throu
arXiv:2610.12704v1 Announce Type: cross Abstract: Federated learning allows dispersed oilfield sites to train a shared intrusion detector without pooling network traffic, yet its aggregation step forc
Cheeky Pint: Q&A with Mark Zuckerberg and Alexandr Wang on the Muse app, Muse Wonder, the risks of committing $100B+ to AI, rebooting Meta's AI team, agentic commerce, more — As Meta scales its AI inf
EXL3-QLoRA I've built this over the last few months and I think it's stable enough to share now. A fork of ExLlamaV3, this is a native ExLlamaV3 training implementation with plain PyTorch, without tra
arXiv:2610.13811v1 Announce Type: cross Abstract: Large language models (LLMs) have shown strong results in classical code generation and are increasingly used to write the unit tests that safeguard t
arXiv:2610.13152v1 Announce Type: new Abstract: Open coding agents are commonly trained through supervised fine-tuning on interaction trajectories whose final patches pass the benchmark test suite. Ho
After running a benchmark test on Exo in Opencode and being amazed by the result, I thought I'd try other models on Opencode. Many were surprisingly terrible. Especially some mid level models. Earlier
Introducing QwenGyre, bringing elastic RL to extreme-long-horizon (XLong) agent training. It launches with two core designs: - Elastic Scheduler: reallocates GPUs between rollout & training as demand
Here're results from my final test of coding, coding (panda/numpy), data analysis, data-driven decision-making, and local RAG domains I interact with most often. This test, which is refined from a 500
Write-up, serve command and raw data: https://github.com/lukolszewski/vllm This shows vLLM fixes and setup that let you put PLE on SSD and save 108GB of system RAM, use int8 kv and squeeze more users
arXiv:2610.13041v1 Announce Type: new Abstract: Recurrent-depth language models improve inference-time reasoning by repeatedly applying a shared network to refine internal representations, but the add
arXiv:2610.13789v1 Announce Type: new Abstract: Momentum methods such as STORM and second-order momentum track the gradient by adding a transport correction to momentum, at the cost of an extra oracle
arXiv:2610.13578v1 Announce Type: cross Abstract: Pre-trained robot policies, such as Vision-Language-Action (VLA) models, provide a strong foundation for generalist robotic manipulation, but adapting
arXiv:2610.13889v1 Announce Type: new Abstract: As AI agents increasingly rely on external tools, accurate retrieval is essential for reliable behavior. Existing methods optimize semantic relevance bu
arXiv:2610.13568v1 Announce Type: new Abstract: We present Rationally Linearized Multilayer Perceptrons(RaLiMPs), a new approach to efficiently linearizing MLPs using low-degree rational approximation
arXiv:2610.12586v1 Announce Type: new Abstract: Event sequences are chains of random events, each described by heterogeneous (numerical and categorical) features. The problem of event sequence forecas
arXiv:2505.17244v3 Announce Type: replace-cross Abstract: Large Reasoning Models (LRMs) leverage explicit reasoning traces, known as Chain-of-Thought (CoT) reasoning, to decompose complex problems int
arXiv:2610.13093v1 Announce Type: new Abstract: Autoregressive robot policies rely on action tokenizers to convert continuous action chunks into compact sequences of discrete prediction targets. Exist
I wanted to track grocery spending per item without sending my receipts to anyone, so I built an Android app around a small vision model that reads a photo of a receipt into JSON: store, date, total,
Recommended NVIDIA paper on memory-efficient post-training RL. A very interesting technique for scaling RL for LLMs. The main takeaway is that you can update all of a model's weights with RL and still
arXiv:2606.18328v2 Announce Type: replace Abstract: Intelligent robots should not only recover from failures, but also acquire the abstract knowledge needed to avoid them in the future. While reinforc
arXiv:2610.13292v1 Announce Type: new Abstract: Lagrangian Neural Networks (LNNs) learn mechanical systems from trajectory data by parameterizing a scalar Lagrangian and deriving the dynamics through
arXiv:2610.12668v1 Announce Type: cross Abstract: Language model agents increasingly operate over long interaction streams, requiring online adaptation to distribution shifts through continual learnin
arXiv:2610.12769v1 Announce Type: cross Abstract: Unlearning in large reasoning models (LRMs) requires removing forget-set information from both the reasoning trace and the final answer. Existing appr
arXiv:2610.13797v1 Announce Type: new Abstract: Detecting communicative meaning in dialogue requires modeling not only lexical content but also the participant-role structures through which sentiment,
arXiv:2610.13453v1 Announce Type: new Abstract: Reinforcement Learning (RL) substantially improves planning performance in autonomous-driving Vision-Language-Action (VLA) models. However, existing RL
arXiv:2610.12601v1 Announce Type: new Abstract: Prompt optimization is an attractive alternative to reinforcement learning for adapting language-model agents, since it is cheap and produces human-read
arXiv:2610.12772v1 Announce Type: new Abstract: Humans effortlessly react to the world; they adeptly return a tennis shot, catch a falling cup, step aside from a passing cart, or pass a box tossed dur
arXiv:2506.11849v3 Announce Type: replace-cross Abstract: With origins in game theory, probabilistic values like Shapley values, Banzhaf values, and semi-values have emerged as a central tool in expla
arXiv:2610.13399v1 Announce Type: new Abstract: Long-term personalized tutoring requires language models to translate a learner's evolving history into appropriate instructional support. Existing LLM-
arXiv:2610.12848v1 Announce Type: new Abstract: In maximum entropy and behavior-constrained reinforcement learning (RL), the optimal policy is given by a Boltzmann distribution. Generating samples fro
arXiv:2610.12710v1 Announce Type: new Abstract: Long-horizon manipulation requires robots to retain task-relevant history while revising conclusions no longer supported by physical evidence. Retaining
arXiv:2610.13778v1 Announce Type: cross Abstract: State-space models (SSMs) maintain a fixed-size recurrent state, but reading and writing it at every decoding step can bottleneck hybrid models. This
ReplaySSM stores an SSM state as a high‑precision checkpoint plus a buffer of recent inputs, cutting memory traffic by ~50 % and accelerating SSM decoding kernels on NVIDIA Blackwell Ultra B300 GPUs b
Amazon.com Inc. is reportedly engaged in discussion over the potential acquisition of artificial intelligence developer Decart.ai Inc. in a deal that could be worth up to 7 billion. Decart has develop
arXiv:2610.12781v1 Announce Type: new Abstract: Aligning two independently pretrained unimodal encoders typically demands millions of paired examples. In this paper, we study the regime where only N s
arXiv:2610.13516v1 Announce Type: cross Abstract: Runtime failure monitors for robot policies are typically evaluated by how accurately they distinguish failed from successful executions. Yet an accur
arXiv:2610.13225v1 Announce Type: cross Abstract: Generative modeling for discrete data has been significantly advanced by learning continuous vector fields on the statistical manifolds to transport s
arXiv:2610.13205v1 Announce Type: new Abstract: On-policy distillation (OPD) trains a target policy on its own rollouts using token-level supervision from a stronger teacher, but typically relies on t
arXiv:2610.12898v1 Announce Type: new Abstract: In continuous diffusion language models (DLMs), latents generated by the diffusion prior are mapped almost deterministically to tokens, either by a deco
arXiv:2610.13678v1 Announce Type: new Abstract: Prior work suggests fraudulent scientists write their articles with higher rates of linguistic obfuscation than genuine scientists, with a possible mech
arXiv:2610.13510v1 Announce Type: new Abstract: Clinical prognosis requires integrating structured measurements, physiological waveforms, longitudinal history, and population context. We introduce PRI
arXiv:2610.13841v1 Announce Type: new Abstract: Coding agents often make useful progress before they fail, but retry-from-scratch discards the machine state created along the way. This makes failure r
arXiv:2610.13440v1 Announce Type: cross Abstract: Recent accent classification systems can achieve high accuracy in standard in-corpus evaluations. However, when speakers overlap between the training
arXiv:2610.13909v1 Announce Type: cross Abstract: While deep learning models for tabular data have recently received significant research attention, the choice of objective functions for regression ta
arXiv:2610.12822v1 Announce Type: new Abstract: Multi-agent systems are increasingly used to solve coding tasks by coordinating agents that share code and plans. These agents are often optimized with
arXiv:2610.13403v1 Announce Type: new Abstract: Reliable real-time failure detection is critical for deploying learned robotic policies, yet defining failures explicitly is infeasible in open-world se
arXiv:2610.12670v1 Announce Type: new Abstract: We consider planning for unmanned aerial vehicle (UAV) and unmanned ground vehicle (UGV) teams in aerial monitoring missions with ordering requirements
arXiv:2610.12865v1 Announce Type: new Abstract: Existing convergence guarantees for non-log-concave sampling with stochastic gradient Langevin Monte Carlo (SG-LMC) typically assume globally Lipschitz
arXiv:2607.16004v2 Announce Type: replace-cross Abstract: Increases in photovoltaic generation, charging of electric vehicles and heat-pump demand challenge operating limits in low-voltage distributio
arXiv:2610.13172v1 Announce Type: new Abstract: World models enable large language model (LLM) agents to anticipate action effects and make informed decisions. For generalization, it is desirable for
arXiv:2610.13438v1 Announce Type: new Abstract: Reinforcement learning (RL) has emerged as a key paradigm for improving large language model (LLM) agents, enabling stronger reasoning, planning, and to
arXiv:2602.00183v2 Announce Type: replace-cross Abstract: Deep neural networks are highly susceptible to backdoor attacks, yet most defense methods to date rely on balanced data, overlooking the perva
arXiv:2610.13912v1 Announce Type: new Abstract: Recursive self-improvement (RSI) aims to transform interaction experience into persistent improvements, yet external feedback is costly and world-model
Learn how to deploy one large language model across two GPU nodes on Amazon EKS using the multi-node Ray LLM Deep Learning Containers, with separate prefill and decode nodes behind one OpenAI-compatib
I get a lot of hate whenever I tell people I run a Q4 quant of Qwen3.8 27B with 262k KV 80t/s with vision, all while running 2 screens on windows on the same card. People seem to think I am lying or m
arXiv:2610.13527v1 Announce Type: cross Abstract: Multimodal language models (MLLMs) exhibit promising spatial reasoning capabilities, yet the internal mechanisms supporting them remain poorly underst
arXiv:2610.13202v1 Announce Type: cross Abstract: Fast rollout generation for long-context reinforcement learning with verifiable rewards (RLVR) requires reducing KV-cache traffic without changing the