On Unlearning for Time-series Forecasting
arXiv:2610.02865v1 Announce Type: new Abstract: Time-series forecasting is widely used in sensitive domains. Models in these settings are often trained on longitudinal user- or entity-level records, w
Knowledge catalogue
arXiv:2610.02865v1 Announce Type: new Abstract: Time-series forecasting is widely used in sensitive domains. Models in these settings are often trained on longitudinal user- or entity-level records, w
arXiv:2610.02413v1 Announce Type: new Abstract: LLM agents increasingly rely on activation probes as runtime monitors for prompt injection, jailbreaks, and unsafe requests, reading the model's own hid
arXiv:2610.02242v1 Announce Type: cross Abstract: Chemical reaction-condition optimization -- choosing the catalyst, ligand, solvent, reagent, temperature, time, and atmosphere that jointly maximize y
arXiv:2610.02981v1 Announce Type: new Abstract: Source-Free Domain Adaptation (SFDA) aims to adapt a source-pretrained model to an unlabeled target domain without access to the original source domain.
arXiv:2610.02826v1 Announce Type: new Abstract: Successful trajectories on difficult tasks provide valuable supervision for model improvement, but specialized harnesses introduce interventions that ma
arXiv:2610.02324v1 Announce Type: cross Abstract: Foundation multimodal large language models are designed to support a broad spectrum of capabilities across diverse domains. Multi-teacher on-policy d
My setup is two RTX 5070 Ti 16GB cards (the second one is on an OCuLink dock) with 64GB of RAM, Ollama on Windows, and the agent runs on pi in WSL. Until last night the daily model was Qwen3.8 27B UD-
arXiv:2610.02599v1 Announce Type: new Abstract: Sustainable protein discovery lacks the fast computational proxies, analogous to molecular docking or density functional theory, that accelerate drug an
arXiv:2610.02959v1 Announce Type: new Abstract: Recent text-to-image models have made substantial progress in photorealism, aesthetics, and text-image alignment. Yet visually appealing images can stil
arXiv:2610.02404v1 Announce Type: cross Abstract: We study long context language models. Instead of training long context natively, or designing a long context harness, we train a model over the simpl
Anthropic Reports Florida Woman's Claude 'Diary' Threat to Law Enforcement And this time it wasn't the AI model that made the LEO referral. It was the 'human review team'. The frontier AI companies ar
First of all, thank you for reading. I trained a small MoE model completely from scratch (no external base weights) and wanted to share the results + a couple of lessons. Apex-2 - Architecture: Decode
arXiv:2610.00952v1 Announce Type: cross Abstract: Recaptioned image-text corpora are now standard for text-to-image (T2I) training, with vision--language model (VLM) captioners replacing sparse alt-te
arXiv:2610.00831v1 Announce Type: new Abstract: A typed decision is a choice among a fixed set of options, returned as a probability rather than as text. Systems that need typed decisions today use mo
arXiv:2602.18182v5 Announce Type: replace-cross Abstract: AI evaluation has primarily focused on measuring capabilities, with formal approaches inspired from Item Response Theory (IRT) being increasin
arXiv:2610.00321v1 Announce Type: cross Abstract: Speculative decoding accelerates large language model inference by drafting future tokens cheaply and verifying them with the target model in parallel
arXiv:2610.02173v1 Announce Type: new Abstract: Ablate a component of a language model, and other components often appear to adjust and compensate. This phenomenon, termed self-repair, has been observ
arXiv:2610.01620v1 Announce Type: new Abstract: Federated training of foundation models is constrained by client memory and communication costs. LoRA-based methods reduce these costs through low-rank
arXiv:2610.00580v1 Announce Type: new Abstract: In collaborative foundation model fine-tuning, client data is rarely homogeneous. Instead, clients typically possess unknown mixtures of distinct data d
arXiv:2610.00196v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have shown strong potential for video understanding and caption generation, but their performance may decline i
arXiv:2610.00948v1 Announce Type: cross Abstract: The executable harness surrounding a GUI model determines how observations are assembled, actions are executed, and verification, recovery, and termin
arXiv:2505.22767v4 Announce Type: replace-cross Abstract: Dialogue with a large language model can lead a person to insight: a sudden change in how they understand a problem. This perspective asks how
arXiv:2610.00426v1 Announce Type: new Abstract: We introduce IrekoGPT, a post-hoc method for converting pretrained LLMs into slimmable models whose width can be adjusted at inference time. Building on
arXiv:2610.00437v1 Announce Type: new Abstract: LLM agents generate intermediate reasoning and actions token by token, making extended interactions slow and computationally expensive. Jev-style models
arXiv:2610.01172v1 Announce Type: new Abstract: We study learning rate (LR) scaling for hybrid architectures combining Transformer and State-Space Model (SSM) blocks, a class adopted by several recent
arXiv:2610.00370v1 Announce Type: new Abstract: Station weather forecasting is fundamentally shaped by both complex spatial dependencies across stations and strong physical coupling among weather vari
arXiv:2610.01936v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated remarkable fluency across many tasks but remain limited by their static, parameter bound knowledge and th
arXiv:2610.02002v1 Announce Type: cross Abstract: Large Language Model (LLM) agents now take part in organizational work, where many authors record decisions across documents over months. Because a re
arXiv:2505.17613v2 Announce Type: replace Abstract: Automatically evaluating multimodal generation presents a significant challenge, as automated metrics often struggle to align with human evaluation,
arXiv:2610.00367v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models enable parameter scaling with limited per-token computation by activating only a small subset of experts for each token,
arXiv:2610.00057v1 Announce Type: new Abstract: Guiding a tractor along a predefined reference path is a key component of precision agriculture. This study develops a path tracking controller based on
arXiv:2609.33149v2 Announce Type: replace Abstract: A common principle of effective learning is to practice material that is neither already mastered nor too difficult to permit progress. We ask how t
arXiv:2606.13607v3 Announce Type: replace Abstract: When large language models (LLMs) fail to generalize or make content-sensitive errors in reasoning, it is often taken as evidence that LLMs are not
arXiv:2610.00424v1 Announce Type: cross Abstract: Knowing how much a causal predictor could improve need not reveal the gain of the repair actually learned. We quantify this gap in a scalar Gaussian c
arXiv:2610.00041v1 Announce Type: cross Abstract: Agent frameworks increasingly delegate work by forking sub-agents; a common default makes the child inherit the parent's full working context. We meas
arXiv:2610.00438v1 Announce Type: new Abstract: Humanoid whole-body manipulation has advanced rapidly, enabling policies to coordinate locomotion, posture, bimanual interaction, and dexterous hand mov
arXiv:2610.00953v1 Announce Type: cross Abstract: An answer candidate in a masked diffusion MLLM can stabilize while its rationale is still unfolding. We distinguish retrospective stabilization of the
arXiv:2609.39702v1 Announce Type: new Abstract: Adapting a language model to a specialized corpus means choosing which instruction-tuning tasks to train on under a fixed budget, and testing one choice
arXiv:2609.39183v1 Announce Type: new Abstract: This paper studies extbf{thinking--answer consistency} in vision-language models. We focus on Visual Intention Grounding, where a model infers a target
arXiv:2609.39629v1 Announce Type: new Abstract: Differential privacy (DP) in machine learning is typically achieved by adding noise to model parameters (private learning) or to model outputs (private
arXiv:2609.38733v1 Announce Type: new Abstract: Recent LLM-based approaches to control either invoke a language model to select actions or synthesize world models that require planning at every decisi
arXiv:2609.39955v1 Announce Type: new Abstract: Single-step retrosynthesis models are commonly evaluated by their ability to recover recorded reactions. In practice, chemists may need to choose among
arXiv:2609.40340v1 Announce Type: new Abstract: Evolutionary search with large language models (LLMs) can stall when progress requires external knowledge the model lacks. Supplying relevant documents
arXiv:2609.38334v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed as agents for multi-step decision-making, yet transfer poorly to unseen environments. World-model
arXiv:2609.39279v1 Announce Type: cross Abstract: Machine unlearning has emerged as a crucial mechanism for removing hazardous knowledge and enforcing safety alignment in Large Language Models (LLMs).
arXiv:2609.39600v1 Announce Type: cross Abstract: Autoregressive (AR) grounding models serialize spatial predictions, introducing sequential latency and imposing a causal order on output tokens. We vi
arXiv:2609.38332v1 Announce Type: cross Abstract: Test-time scaling improves model performance by allocating additional compute during inference. Using this compute effectively across multiple context
arXiv:2609.40295v1 Announce Type: new Abstract: Web text makes up the majority of pretraining data and is increasingly AI-generated. After applying FineWeb quality filtering, we find that 27.5% of tok
arXiv:2609.38362v1 Announce Type: new Abstract: Generative vision-language models (VLMs) such as Qwen-VL and LLaVA achieve strong zero-shot performance on tasks overlapping with their pretraining dist
arXiv:2609.39588v1 Announce Type: new Abstract: We push the frontier of large-scale spatial intelligence in Vision-Language Models (VLMs) and introduce the first benchmark that probes geographical lay
arXiv:2609.38764v1 Announce Type: new Abstract: Language models are typically pretrained from random initialization. Recent work challenges this convention, showing that a brief warm-up on abstract, a
arXiv:2609.40089v1 Announce Type: new Abstract: Continued pretraining enables language models to adapt to new domains and knowledge, but often at the cost of forgetting previously acquired capabilitie
arXiv:2609.35470v1 Announce Type: cross Abstract: Applied researchers increasingly convert images into features with pretrained encoders, then use those features in a downstream prediction model. The
arXiv:2609.38847v1 Announce Type: cross Abstract: Rubric-based reinforcement learning (Rubric-RL) trains language models where no verifier exists. A judge checks each criterion of a rubric, and the ve
arXiv:2609.39049v1 Announce Type: cross Abstract: A large language model (LLM) can rate depression severity directly from a social media post or mark which clinical criteria the post shows and let cod
arXiv:2609.39827v1 Announce Type: cross Abstract: Pre-pretraining (PPT) on synthetic non-natural language data improves token efficiency during language model pre-training (PT). Prior work attributes
arXiv:2609.38389v1 Announce Type: cross Abstract: Large language models (LLMs) remain vulnerable to adversarial attacks that circumvent safety alignment to elicit harmful outputs. It remains unclear h
arXiv:2609.39464v1 Announce Type: new Abstract: In federated averaging, local objectives can admit multiple optimal heads, making the aggregate depend on which heads clients return. We study this ambi
arXiv:2609.39199v1 Announce Type: cross Abstract: Large Audio Language Models (LALMs) rely on effective audio encoders for multi-task performance. We introduce UniAE-MoE, a unified audio encoder desig
arXiv:2609.36337v1 Announce Type: new Abstract: Tabular foundation models achieve strong performance by conditioning on labelled examples in context, but softmax attention limits their use on large da