Knowledge catalogue
arXiv:2605.25648v1 Announce Type: cross Abstract: This paper proposes StrTransformer, a source-wise structured Transformer framework for blind source recovery and branch-wise latent modeling. Instead
arXiv:2605.24690v1 Announce Type: cross Abstract: The motion planning problem for robotic manipulation can be addressed through classical or deep learning approaches. Existing methods face significant
arXiv:2605.24556v1 Announce Type: cross Abstract: Multilingual retrieval increasingly underpins cross-lingual question answering and retrieval-augmented generation. Strong zero-shot scores on multilin
arXiv:2605.25880v1 Announce Type: new Abstract: Large-scale transformer training and deployment are increasingly constrained by the transfer of activations, gradients, and optimizer states across acce
Today's Training Data episode takes us BTS on the infrastructure challenges required to do large RL runs at scale, featuring @ellev3n11 (Composer Lead at @cursor_ai) and @dzhulgakov (Co-Founder at @Fi
arXiv:2602.22631v2 Announce Type: replace-cross Abstract: Neural networks are increasingly deployed in scientific, safety critical, and mission critical pipelines, yet verification and analysis are of
arXiv:2602.01914v2 Announce Type: replace Abstract: Token attribution methods provide intuitive explanations for language model outputs by identifying causally important input tokens. However, as mode
arXiv:2605.23989v1 Announce Type: new Abstract: Agentic AI systems -- Large Language Models (LLMs) augmented with planning, tool use, memory, and long-horizon interactions -- can execute complex tasks
arXiv:2605.25731v1 Announce Type: new Abstract: Multi-trait essay scoring aims to provide fine-grained evaluation of writing quality across multiple dimensions. However, how to effectively post-train
arXiv:2511.19065v2 Announce Type: replace-cross Abstract: MeanFlow promises high-quality generative modeling in few steps, by jointly learning instantaneous and average velocity fields. Yet, the under
arXiv:2212.07944v3 Announce Type: replace Abstract: We study a multi-factor block model for variable clustering and connect it to regularized subspace clustering through a distributionally robust vers
arXiv:2510.15514v3 Announce Type: replace Abstract: Reinforcement Learning from AI Feedback (RLAIF) relies on LLM judges as preference measurement instruments, yet these instruments are fundamentally
arXiv:2509.21592v2 Announce Type: replace-cross Abstract: We consider the problem of forecasting motion from a single image, i.e., predicting how objects in the world are likely to move, without the a
arXiv:2510.16435v2 Announce Type: replace-cross Abstract: With the growing use of large language models and conversational interfaces in human-robot interaction, robots' ability to answer user questio
arXiv:2605.24202v1 Announce Type: new Abstract: Multi-agent LLM workflows route inference through specialized roles to lift end-task accuracy, but jointly training those roles with reinforcement learn
You can’t build an autonomous agent on a static RAG pipeline. Because goals mutate dynamically, agents require an advanced knowledge infrastructure, rather than forcing the model to hunt through a raw
arXiv:2605.05997v2 Announce Type: replace Abstract: Dynamic spatial reasoning from monocular video is essential for bridging visual intelligence and the physical world, yet remains challenging for vis
arXiv:2605.23258v1 Announce Type: new Abstract: KV cache growth is a major bottleneck for long-context inference in large language models. Existing methods are often dominated by binary eviction or re
arXiv:2605.23247v1 Announce Type: new Abstract: In this paper, we introduce the first machine learning framework for predicting optimal processing times in Single-Level Tree Network (SLTN) architectur
arXiv:2601.22367v2 Announce Type: replace-cross Abstract: Generalized Bayesian Inference (GBI) tempers a loss with a temperature eta > 0 to mitigate overconfidence and improve robustness under model m
arXiv:2605.23454v1 Announce Type: new Abstract: Rubric-based rewards offer a promising way to extend reinforcement learning (RL) for large language models beyond tasks with automatically verifiable an
arXiv:2601.22324v2 Announce Type: replace Abstract: Modern clinical practice relies on evidence-based guidelines implemented as compact scoring systems composed of a small number of interpretable deci
arXiv:2605.23780v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) need efficient mechanisms to update knowledge without degrading existing capabilities. While intrinsic multimod
arXiv:2407.03535v3 Announce Type: replace Abstract: Low-light videos often exhibit spatiotemporally incoherent noise, compromising visibility and degrading performance in computer vision applications.
arXiv:2605.23569v1 Announce Type: new Abstract: Dynamic Programming (DP) and Constraint Programming (CP) are well-established paradigms for solving combinatorial optimization problems. Usually, these
arXiv:2605.22845v1 Announce Type: cross Abstract: Finite element simulations of large-deformation sheet material forming involve node-element coupling between nodal kinematics and element-level deform
arXiv:2605.23635v1 Announce Type: cross Abstract: Traditional neural networks provide deterministic predictions without inherent uncertainty estimates. While Bayesian Neural Networks (BNNs) offer a pr
arXiv:2605.23493v1 Announce Type: new Abstract: On-Policy Distillation (OPD) has gained wide attraction as an LLM post-training paradigm due to its effectiveness in improving capabilities without intr
arXiv:2605.23328v1 Announce Type: new Abstract: Emotion Recognition in Conversation is a core component of affective computing, while current resources of sign language emotion datasets primarily focu
arXiv:2605.23854v1 Announce Type: new Abstract: Bradley-Terry-Luce (BTL) model estimation is a well-established strategy to rank a collection of items given a dataset of pairwise comparisons. Although
arXiv:2605.23191v1 Announce Type: new Abstract: Scaling recommendation models is a central challenge in recommender systems. Recently, RankMixer has emerged as an effective solution, operating on a un
Figure AI livestreamed three humanoid robots (F.03 models) autonomously sorting packages for over 24 hours continuous operation without failure, extending their original 8-hour target . The robots sor
arXiv:2605.23903v1 Announce Type: new Abstract: Camera-controlled video generation has achieved remarkable progress in recent years. However, existing video-to-video re-rendering methods primarily rel
arXiv:2605.23602v1 Announce Type: new Abstract: Existing 3DGS methods effectively render high-quality novel views in clear-day scenes. However, they struggle with night scenes, particularly in glow re
arXiv:2602.11629v2 Announce Type: replace Abstract: Graph Prompt Learning (GPL) has recently emerged as a promising paradigm for downstream adaptation of pre-trained graph models, mitigating the misal
arXiv:2602.00979v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly deployed as educational agents for automatic short answer grading (ASAG) in real-world education
arXiv:2605.23867v1 Announce Type: cross Abstract: Large language models (LLMs) have the potential to aid and improve human decision-making in classification tasks, not only by providing fairly accurat
arXiv:2605.23362v1 Announce Type: new Abstract: Evaluating large language models increasingly relies on LLM-as-a-judge protocols, but such evaluations remain costly: different judges have different pr
arXiv:2605.23878v1 Announce Type: new Abstract: Modern video generators produce visually compelling clips but still struggle with physical and motion consistency, limiting their use as reliable world
arXiv:2605.22976v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly integrated into software systems for diverse purposes, due to their versatility, flexibility, and abilit
arXiv:2605.23723v1 Announce Type: new Abstract: Large language model agents increasingly rely on persistent memory to store past interactions, retrieve relevant demonstrations, and improve long-horizo
arXiv:2605.23482v1 Announce Type: cross Abstract: Dataset distillation compresses large training sets into compact synthetic datasets while preserving downstream performance. As modern systems increas
arXiv:2605.23192v1 Announce Type: new Abstract: Video editing has recently achieved remarkable progress with diffusion-based generative models, enabling diverse object-level manipulations from natural
arXiv:2605.23478v1 Announce Type: cross Abstract: Accurate crop yield prediction is crucial for sustainable agriculture and global food security. While existing methods are predominantly developed for
arXiv:2605.23128v1 Announce Type: new Abstract: Currently, Vision-Language-Action (VLA) models have become the most adopted paradigm for robotic manipulation for its great potential for task generaliz
arXiv:2605.22856v1 Announce Type: cross Abstract: Channel foundation models assume access to fully observed channels, an assumption that fails in deployment. We introduce PilotWiMAE, a self-supervised
arXiv:2510.11195v2 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) increases the reliability and trustworthiness of the LLM response and reduces hallucination by eliminatin
arXiv:2605.11215v2 Announce Type: replace-cross Abstract: Pre-training large language models on massive GPU clusters has made hardware faults routine rather than rare, driving the need for resilient t
arXiv:2605.23115v1 Announce Type: new Abstract: Bike-sharing models trained on historical station-hour data may degrade when deployed in later years because travel patterns change over time. This pape
arXiv:2605.23406v1 Announce Type: new Abstract: End-to-end autonomous driving solutions, which directly process multimodal sensory data and output fine-grained control commands, have gradually become
arXiv:2603.23565v2 Announce Type: replace-cross Abstract: Safe reinforcement learning (RL) is a standard paradigm for safety-critical decision making. However, real-world safety constraints can be com
arXiv:2605.05704v2 Announce Type: replace-cross Abstract: Recent advances in foundation models have transformed LLMs from passive conversational systems into autonomous agents capable of reasoning and
arXiv:2605.23411v1 Announce Type: cross Abstract: Test-time adaptation (TTA) effectively counters distribution shifts but exposes models to adversarial manipulation via the unlabeled test stream. Exis
arXiv:2602.02780v3 Announce Type: replace Abstract: Large language models (LLMs) are enabling reasoning over 2D and 3D structures, yet existing methods remain modality-specific and typically compress
arXiv:2605.23180v1 Announce Type: new Abstract: We propose to improve in-context learning (ICL) by optimizing the continuous embeddings of a fixed few-shot prompt at test time. The key observation is
arXiv:2605.23592v1 Announce Type: new Abstract: Dismantling aircrafts reaching their end of life is a complex endeavour that is necessary in terms of sustainability but yields small income margins for
arXiv:2603.10453v2 Announce Type: replace Abstract: This study proposes a multi-resolution Convolutional Long Short-Term Memory (ConvLSTM) ensemble framework that leverages diverse temporal input reso
arXiv:2605.23040v1 Announce Type: new Abstract: Latent steering exploits internal representations of Large Language Models (LLMs) to guide generation, yet interventions on dense states can entangle di
arXiv:2507.23372v2 Announce Type: replace Abstract: Emotional understanding and generation are often treated as separate tasks, yet they are inherently complementary and can mutually enhance each othe
arXiv:2507.05064v4 Announce Type: replace-cross Abstract: Gaussian processes are flexible, probabilistic, non-parametric models widely used in machine learning and statistics. However, their scalabili