Knowledge catalogue
arXiv:2610.17089v1 Announce Type: new Abstract: Existing embodied navigation tasks commonly assume that traversability and object states remain fixed during an episode. Yet reaching a goal may require
arXiv:2610.18684v1 Announce Type: cross Abstract: Personal-agent memory has largely focused on learning what users know, prefer, and want. However, knowing the user does not necessarily mean knowing w
arXiv:2610.16634v1 Announce Type: cross Abstract: Recent Vision-Language-Action (VLA) models increasingly use natural-language instructions to condition autonomous driving behavior. Yet existing close
arXiv:2610.16644v1 Announce Type: new Abstract: Learning a response law for continuous decisions from observational time series is central to many real-world decision systems, yet temporal non-station
arXiv:2610.14351v1 Announce Type: new Abstract: World-action models inherit broad visual and physical priors from video pre-training. However, standard within-video next-frame prediction allows them t
arXiv:2610.17877v1 Announce Type: new Abstract: Reusing Transformer blocks offers a way to increase diffusion-model computation at test time, but naive recurrence can degrade generation beyond its tra
arXiv:2610.17637v1 Announce Type: new Abstract: Since scaling laws were introduced for modern LLMs (Kaplan et al., 2020), several works have extended them to account for quantization, tracking the eme
arXiv:2601.14628v2 Announce Type: replace Abstract: Vision-language-action (VLA) models inherit powerful semantic representations from large language models, but carrying over their design priorities
arXiv:2610.14191v1 Announce Type: new Abstract: Forecasting tissue deformation from future instrument motion could support predictive planning and increasingly autonomous surgical systems. We study th
arXiv:2610.15078v1 Announce Type: new Abstract: Machine-learned interatomic potentials (MLIPs) accelerate molecular dynamics (MD) simulations by learning the energies and forces that govern atomic mot
arXiv:2610.16129v1 Announce Type: new Abstract: Deploying LLM agents in non-stationary environments requires continually revising their instructions as the task drifts, yet rewriting after every repor
arXiv:2610.14335v1 Announce Type: new Abstract: Latent world-model planning has shown promising results in goal-conditioned robotic manipulation, but remains challenging for long-horizon planning due
arXiv:2610.15537v1 Announce Type: cross Abstract: Typed decision interfaces restrict models to predefined actions, yet schema-valid choices can still trigger policy-violating state changes. Evaluating
arXiv:2610.13991v1 Announce Type: new Abstract: Self-evolving agents improve through repeated cycles of modification and evaluation. However, existing methods receive feedback on modifications only af
arXiv:2610.14001v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) uses a self-teacher conditioned on privileged information to turn the sparse outcome signal of reinforcement learning
arXiv:2610.14635v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) have achieved remarkable progress across a wide range of multimodal tasks. However, object hallucination remains
arXiv:2610.16409v1 Announce Type: new Abstract: Repetitive structures can give an incorrect pose candidate more inlier support than an accurate one, causing visual localization to select it. History-G
arXiv:2610.17590v1 Announce Type: new Abstract: Diffusion language models (DLMs) have attracted wide attention for their fast, parallel decoding, but they are believed to be far less efficient to trai
arXiv:2610.16242v1 Announce Type: new Abstract: World-action models should preserve the intended manipulation across equivalent descriptions of a spatial goal. We evaluate this consistency in 864 roll
arXiv:2610.17080v1 Announce Type: new Abstract: Unified multimodal models (UMMs) provide an interface for interleaved text-image generation, where generated visual states can directly inform subsequen
arXiv:2610.16946v1 Announce Type: new Abstract: Descriptions of how people use AI are becoming training data for the next generation of models. We ask whether what a model reads about its users change
arXiv:2610.18459v1 Announce Type: new Abstract: External tools can extend the capabilities of small language models (SLMs), enabling their deployment in resource constrained environments. However, the
arXiv:2404.14855v2 Announce Type: replace Abstract: We characterize the geometry of the set of all weight vectors for which a fully-connected linear neural network computes the same linear transformat
arXiv:2610.15589v1 Announce Type: new Abstract: Many deployed distillation pipelines show the student a truncated view of the teacher: keep the top-k probabilities, renormalize, and minimize a diverge
arXiv:2610.15807v1 Announce Type: new Abstract: Generating coherent videos grounded in a unified underlying world remains a major challenge, particularly under large viewpoint changes, where existing
arXiv:2610.14683v1 Announce Type: new Abstract: Large language model (LLM)-based AI Scientists advance scientific discovery, yet they suffer from inefficiencies due to noisy observations. Existing pri
arXiv:2610.18853v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) relies on costly model-generated responses, motivating larger rollout batches and square-root lear
arXiv:2610.15915v1 Announce Type: new Abstract: Reusable skills improve multimodal agents without updating model weights, but their effectiveness depends on both the evidence presented and the procedu
arXiv:2610.15139v1 Announce Type: new Abstract: Linear-attention and state-space LLMs carry long context in a fixed-size recurrent state, and quantizing that state is the natural way to cut its cost d
arXiv:2610.14009v1 Announce Type: new Abstract: Large AI models increasingly rely on distributed GPU execution, yet it remains unclear whether established failure analysis methods transfer effectively
arXiv:2610.15929v1 Announce Type: new Abstract: Recent trackers built on foundation models such as the Segment Anything Model (SAM) achieve strong performance by propagating object masks through memor
arXiv:2610.17806v1 Announce Type: new Abstract: Collision rate remains a dominant metric for evaluating autonomous driving trajectory safety, but its binary nature obscures substantial safety differen
New version of my MiniMax H3 timeline workflow released Some very important bug fixes included, and a lot of improvements. The YouTube video above includes a lot of tips for using the workflow in addi
arXiv:2603.03753v2 Announce Type: replace-cross Abstract: The ongoing shift of Artificial Intelligence (AI) from centralized cloud application programming interfaces (APIs) to local inference on edge
arXiv:2610.13078v1 Announce Type: new Abstract: Safety-aligned large language models (LLMs) remain vulnerable to jailbreaks and can over-refuse benign requests. Understanding these failures requires d
arXiv:2610.13521v1 Announce Type: new Abstract: Multi-teacher on-policy distillation (MOPD) extends on-policy distillation (OPD) by routing domain-specific data to specialized teachers, integrating th
arXiv:2610.12570v1 Announce Type: new Abstract: Speculative decoding accelerates large language model inference by using a lightweight drafter to propose multiple tokens that are subsequently verified
arXiv:2610.13262v1 Announce Type: new Abstract: Memory-dependent manipulation requires a policy to track execution state and recover visual evidence that is no longer observable. We propose dual-strea
arXiv:2610.13773v1 Announce Type: cross Abstract: Multiple-gradient descent is typically formulated in Euclidean geometry, whereas matrix-aware optimizers use directions induced by other norms. We ana
arXiv:2511.01047v4 Announce Type: replace-cross Abstract: Automated program repair (APR) has recently shifted toward large language models and agent-based systems, while prior work shows that reposito
arXiv:2610.13764v1 Announce Type: cross Abstract: Prior-data fitted networks (PFNs) are trained to approximate the Bayesian posterior predictive distribution (PPD) of a synthetic prior, yet results ab
arXiv:2610.13494v1 Announce Type: new Abstract: Existing LLM-based agent approaches for long-horizon machine learning engineering (MLE) often use context engineering, implemented through custom harnes
I've made a few posts recently, just talking about the hardware I've got and the model I use. Pair of P100s, Unsloth Qwen3.6 35b A3B UD Q4 K XL. There's been a ton of talk of model and hardware specif
arXiv:2610.12518v1 Announce Type: cross Abstract: This position paper argues that the generative molecular dynamics (GenMD) community is not properly evaluating its progress: current evaluations let a
arXiv:2610.13534v1 Announce Type: new Abstract: Long-horizon embodied agents must maintain task-relevant information, coordinate heterogeneous robots, and adapt their decisions as execution unfolds. E
arXiv:2610.12575v1 Announce Type: cross Abstract: Modern video-language models are increasingly treated as general-purpose video reasoners, yet it remains unclear whether they robustly capture tempora
arXiv:2610.13630v1 Announce Type: new Abstract: Attention Residuals (AttnRes) enables content-dependent retrieval over network depth, which can be viewed as single-stream softmax attention along the d
arXiv:2610.13390v1 Announce Type: new Abstract: Geospatial machine learning often depends on task-specific feature engineering over large collections of sociodemographic, business, and environmental v
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:2610.12822v1 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:2610.12723v1 Announce Type: new Abstract: Neural surrogates that forecast a physical field from sparse, noisy sensors read a window of nearby sensors and a history of past snapshots. Practitione
arXiv:2610.12599v1 Announce Type: new Abstract: Sparse computation can scale the parametric capacity of LLMs without proportionally increasing active computation, but pretraining sparse architectures
arXiv:2610.13238v1 Announce Type: new Abstract: On-Policy Distillation (OPD) has emerged as a powerful paradigm for transferring reasoning capabilities from frontier models to smaller models, while ex
arXiv:2610.13306v1 Announce Type: new Abstract: Local online training on resource-constrained platforms requires low computational and training-state overhead. We study the numerical stability and com
arXiv:2610.13307v1 Announce Type: new Abstract: The escalating environmental footprint of the Information and Communication Technol- ogy (ICT) sectorwith global Data Center electric- ity usage potenti
arXiv:2610.12981v1 Announce Type: cross Abstract: Visual interventions provide a training-free way to reduce hallucinations in multimodal large language models. However, an intervention may have littl
arXiv:2610.13456v1 Announce Type: new Abstract: Cyber-Physical Systems are developed through multiple model based activities, comprising several stages of development. As the development progresses th
arXiv:2610.13416v1 Announce Type: new Abstract: Large language model (LLM) agents are becoming direct users of the open web. As they take on increasingly complex and information-intensive tasks, effec
arXiv:2605.11928v2 Announce Type: replace Abstract: Tool-use language agents are evaluated on benchmarks that assume clean inputs, unambiguous tool registries, and reliable APIs. Real deployments viol
For what it's worth. I'm a mechanical engineer by education and software engineer in practice over the past ~20 years. Playing around with local models has been a recent hobby. Today I decided to do a