Knowledge catalogue
arXiv:2610.13277v1 Announce Type: cross Abstract: Memory-augmented assistants retrieve evidence from stored conversations and documents to answer queries. Most embedding-based retrievers compare singl
arXiv:2610.13891v1 Announce Type: cross Abstract: Light Detection and Ranging (LiDAR) is critical for autonomous perception, yet its performance is known to degrade in adverse weather. While existing
arXiv:2606.19386v2 Announce Type: replace-cross Abstract: Runtime monitors for autonomous agents commonly threshold an accumulated internal state - a behavioural baseline, a drift statistic, or, in ou
arXiv:2610.12907v1 Announce Type: cross Abstract: Federated vision-language models (FedVLMs) represent one of the emerging frontiers of machine learning, aiming to integrate federated learning within
arXiv:2610.13607v1 Announce Type: new Abstract: Negative polarity items (NPIs), such as 'anymore' and 'ever', are grammatical only in select environments, predominantly in the context of negation. Bec
arXiv:2610.13382v1 Announce Type: new Abstract: Kernel Ridge Regression (KRR) is a theoretically sound algorithm for nonparametric learning, which is also often used to investigate properties of deep
We're launching Precision Numerics by releasing Boole-1.7B, a 1-bit version of Qwen3-1.7B. 247 MB packed weights: 13.9× smaller than BF16. 85.9% of the BF16 model’s average score across our 10-task ev
arXiv:2610.13285v1 Announce Type: new Abstract: Distilling long-chain reasoning trajectories from large teacher models provides an effective way to improve the reasoning ability of small language mode
arXiv:2610.13481v1 Announce Type: new Abstract: On-policy distillation (OPD) provides teacher supervision on student-generated trajectories, but a single trajectory realizes only one continuation at e
arXiv:2505.22184v3 Announce Type: replace-cross Abstract: Social media platforms have experienced a significant rise in toxic content, including abusive language and discriminatory remarks, presenting
arXiv:2603.00530v2 Announce Type: replace Abstract: Sampling from unnormalized densities using diffusion models has emerged as a powerful paradigm. However, while recent approaches that use least-squa
arXiv:2610.12703v1 Announce Type: cross Abstract: High-risk applications of deep learning require precise characterization of model decision-making. We conduct a systematic explainability evaluation a
Write-up: https://zhebrak.io/posts/brokenml/ Repo: https://github.com/zhebrak/brokenml I built a benchmark to determine the access level agents need to successfully fix broken ML workloads (PyTorch ov
arXiv:2610.13862v1 Announce Type: new Abstract: Deploying language-model agents onboard mobile robots requires task reasoning and responsive execution within limited compute and memory. We propose BT-
arXiv:2610.12711v1 Announce Type: new Abstract: Federated Large Language Models (FedLLMs) are promising to deliver privacy-preserving, collaborative intelligence. The decentralized training process is
arXiv:2610.12530v1 Announce Type: new Abstract: Training-free feature reuse accelerates diffusion transformer inference by replacing full denoising computation at selected steps with cached approximat
arXiv:2610.13693v1 Announce Type: cross Abstract: Neural networks (NNs), while highly flexible and versatile, are often poorly calibrated. Post-hoc calibration methods adjust the outputs of an already
arXiv:2610.13105v1 Announce Type: new Abstract: Failure attribution for LLM agents aims to identify decisive steps responsible for task failure, which is critical for debugging and improving agentic s
arXiv:2610.13821v1 Announce Type: new Abstract: A useful language model should know when to answer and when to say 'I don't know.' Can we improve that decision by training the model itself or by train
arXiv:2610.13948v1 Announce Type: new Abstract: Language models increasingly support or automate information retrieval from document collections too large to index. This task is difficult when it requ
arXiv:2610.12644v1 Announce Type: cross Abstract: Backdoor Attacks on Large Language Models (LLMs) typically follow a trigger-response pattern, where satisfying a trigger condition activates a single
arXiv:2610.13257v1 Announce Type: cross Abstract: Cross-tokenizer on-policy distillation (OPD) requires aligning teacher and student sequences before their scores can be compared. Decoded-text alignme
arXiv:2610.12567v1 Announce Type: new Abstract: Prior research on learning from humans often requires real human demonstrations. But advances in video generation models offer a new paradigm: we can no
arXiv:2610.13520v1 Announce Type: new Abstract: Identifying causal effects from observational data typically requires a fully specified causal graph, an assumption that is often unrealistic in complex
arXiv:2610.13064v1 Announce Type: new Abstract: Large Language Model (LLM) agents have demonstrated remarkable capabilities in tackling complex tasks through agentic workflows. However, manually desig
arXiv:2610.13007v1 Announce Type: new Abstract: Learning-based methods have demonstrated strong performance in mapless robot navigation. However, a learned policy remains restricted to the embodiment
arXiv:2610.13929v1 Announce Type: new Abstract: Robot policies often convert sensing and control into fixed-rate observation-action sequences, leaving physical time implicit in sequence position. This
arXiv:2610.12520v1 Announce Type: cross Abstract: The goal of circuit discovery is to decompose a monolithic neural network into tiny modular subnetworks which are interpretable in the sense that each
Cisco Systems Inc. took to the stage at the annual Open Compute Project Global Summit today, unveiling a new suite of open silicon and optical networking systems as it delivered one of the event’s mos
arXiv:2610.12655v1 Announce Type: new Abstract: LLM agents can execute increasingly complex tasks, but effective assistance also requires aligning their actions with goals and constraints that users m
arXiv:2610.13059v1 Announce Type: new Abstract: Radiology reports are essential for diagnostic reasoning and patient care, yet their manual preparation is time-consuming and cognitively demanding. Aut
arXiv:2610.12580v1 Announce Type: new Abstract: Event ontology is the foundational framework for defining events in a dataset. Event type induction generally involves domain experts who define guideli
arXiv:2610.13433v1 Announce Type: cross Abstract: This paper addresses the grid quantization error of deep-learning (DL)-based direction-of-arrival (DOA) estimation. Classification- based DOA methods
arXiv:2610.12849v1 Announce Type: cross Abstract: Current software engineering agents are evaluated predominantly inside isolated sandboxes against synchronous local tests. However, deploying features
arXiv:2602.03806v2 Announce Type: replace-cross Abstract: Training large language models (LLMs) for multi-turn code generation typically relies on online reinforcement learning (RL), in which models l
arXiv:2610.13057v1 Announce Type: cross Abstract: Counterfactual text editing is the ability to revise a given text in light of a hypothetical change while preserving facts not causally affected by th
arXiv:2610.12837v1 Announce Type: cross Abstract: Knowledge distillation aims to train a smaller student model to mimic a larger teacher model for resource-constrained environments. However, the proce
arXiv:2610.12884v1 Announce Type: new Abstract: Accurate estimation of reservoir properties from seismic data remains challenging when well-log labels are sparse but three-dimensional seismic observat
arXiv:2610.12927v1 Announce Type: new Abstract: Large language models (LLMs) excel across diverse tasks, benefiting from knowledge priors, in-context reasoning, and test-time computation. Despite thes
arXiv:2610.12872v1 Announce Type: new Abstract: Large language models (LLMs) demonstrate strong individual task performance, yet still struggle to collaborate with users over extended, multi-turn inte
arXiv:2610.13439v1 Announce Type: cross Abstract: Collective Autonomous Vehicle (AV) route choices in real-world traffic networks can create externalities for Human-Driven Vehicles (HDVs), as routes t
arXiv:2610.13144v1 Announce Type: new Abstract: LLM-based multi-agent systems (MAS) have emerged as a promising paradigm for enhancing complex reasoning through role specialization and collaboration,
arXiv:2610.13804v1 Announce Type: cross Abstract: Gaussian process solvers for linear partial differential equations (PDEs) return posteriors rather than point estimates, but they condition only on eq
arXiv:2610.13570v1 Announce Type: new Abstract: Reasoning models can benefit from test-time scaling, but continued reasoning may become ineffective or harmful, a phenomenon termed overthinking. Evalua
arXiv:2610.13931v1 Announce Type: cross Abstract: The expressivity of a neural network Phi describes the class of functions that a network can express. The term topological expressivity refers to a fa
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:2610.13113v1 Announce Type: cross Abstract: Continual post-training faces a dual challenge of acquisition and retention: models must learn new capabilities while preserving prior knowledge. Whil
arXiv:2610.12915v1 Announce Type: new Abstract: Minimax optimization is fundamental to adversarial learning yet suffers from severe stability challenges, often manifesting as persistent limit cycles o
arXiv:2610.13665v1 Announce Type: new Abstract: This paper presents a dual-quadrotor hook- suspended transport system for cooperative aerial manipulation of a payload that is not rigidly attached to a
arXiv:2610.12776v1 Announce Type: new Abstract: Automatic differentiation (AD) is a cornerstone of modern machine learning. Since all AD frameworks implicitly fix a basis of Euclidean space to define
arXiv:2610.13276v1 Announce Type: new Abstract: Set-based language model routing aims to increase the coverage of the event where at least one model answers a query correctly while controlling the num
arXiv:2610.12514v1 Announce Type: cross Abstract: Autoregressive video diffusion models maintain a growing attention key-value (KV) cache, making memory a key bottleneck for long video generation. Rec
arXiv:2603.05911v2 Announce Type: replace-cross Abstract: Medical image segmentation is undergoing a paradigm shift from conventional visual pattern matching to cognitive reasoning analysis. Although
arXiv:2610.13606v1 Announce Type: cross Abstract: Correlation matrices combine nonlinear positive-definiteness constraints with a simultaneous row-column permutation symmetry. Their generation therefo
arXiv:2610.12775v1 Announce Type: cross Abstract: The two main traditional player statistics used in soccer are goals scored and assists, with an assist credited when a player's pass immediately leads
arXiv:2610.12694v1 Announce Type: new Abstract: Molecular machine learning evaluates out-of-distribution performance with structure disjoint splits, a construction rule fixed once at the scale its lib
arXiv:2412.13844v2 Announce Type: replace-cross Abstract: Retrieval models for recommendation need to account for outcomes such as watch time while searching large item corpora efficiently. We present
arXiv:2610.12830v1 Announce Type: new Abstract: Reasoning post-training draws on offline demonstrations and policy-generated rollouts, yet conventional supervised fine-tuning (SFT) followed by reinfor
arXiv:2610.12826v1 Announce Type: new Abstract: We presented a program that automates the construction and solution of the cubic spline interpolation problem for a sequence of position-time waypoints,
arXiv:2610.13264v1 Announce Type: cross Abstract: On-policy distillation (OPD) reveals versatility and convenience during VLM post-training, providing dense supervision for student from teacher. Howev