Knowledge catalogue
arXiv:2609.22162v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) improves the factuality of large language models (LLMs) and vision-language models (VLMs) by grounding generation i
arXiv:2609.23646v1 Announce Type: cross Abstract: E-commerce search requires distinguishing products that are merely related to a query from those that directly satisfy the user's shopping intent. We
arXiv:2609.22977v1 Announce Type: cross Abstract: Similarity-based retrieval is the dominant rule for conditioning large language models (LLMs) in in-context learning, retrieval-augmented generation,
arXiv:2609.22949v1 Announce Type: cross Abstract: Existing prompt injection research focuses on single-model chatbot scenarios, where an attacker manipulates one LLM through crafted input. Multi-agent
arXiv:2609.22178v1 Announce Type: cross Abstract: Computer-use agents (CUAs) have made rapid progress in completing complex tasks through graphical user interfaces, yet post-training centered on task
arXiv:2609.22582v1 Announce Type: new Abstract: End-to-end and vision-language-action (VLA) driving policies are compared by leaderboard rank, but a rank reports an outcome, not the behaviour behind i
arXiv:2609.22095v1 Announce Type: cross Abstract: Electrodermal activity (EDA) is widely used in automatic stress detection, yet most pipelines treat it only as a raw one-dimensional waveform. This st
arXiv:2609.22149v1 Announce Type: new Abstract: Multimodal synthetic datasets combine structured attributes with free text, but are often evaluated separately. Such metrics can remain high after tabul
arXiv:2609.22291v1 Announce Type: new Abstract: This paper presents a comprehensive experimental evaluation and detailed analysis of state-of-the-art multi-object tracking algorithms, with an emphasis
arXiv:2609.22111v1 Announce Type: new Abstract: Large language model agents are increasingly capable of conducting research autonomously, producing research documents alongside the code and experiment
arXiv:2609.24612v1 Announce Type: new Abstract: Model merging aims to consolidate multiple task-specific models without access to extra training process. However, existing subspace-based methods large
arXiv:2609.23606v1 Announce Type: new Abstract: Mesh texture compression typically relies on 2D UV atlases, whose chart discontinuities and mapping overhead can limit coding efficiency. To tackle this
arXiv:2609.24745v1 Announce Type: new Abstract: World action models generate actions together with visual predictions of their consequences. These paired outputs create the potential for planning by s
Big model release today - I wrote about Claude Opus 5.5, GPT-6 Sol, and GPT-6 Luna - plus comparison grids of pelicans by the different model families at different reasoning levels https://simonwillis
arXiv:2609.23594v1 Announce Type: new Abstract: Orthogonality in a LoRA factor does not by itself specify what the composed update protects: the answer depends on the task-start state, the parameteriz
arXiv:2510.06145v2 Announce Type: replace Abstract: We tackle the problem of forecasting bimanual 3D hand motion and articulation from a single image in everyday settings. To address the lack of 3D ha
arXiv:2609.23717v1 Announce Type: new Abstract: Global vision--language similarities compress an image and a caption into one vector, preserving semantics but not which word corresponds to which regio
arXiv:2609.23445v1 Announce Type: new Abstract: Bimanual manipulation requires policies that coordinate two arms while adapting their functional roles to scene geometry, object configuration, and task
arXiv:2609.23352v1 Announce Type: new Abstract: Bimanual interaction produces complementary tactile views of the same physical process, yet existing tactile representation learning largely models the
arXiv:2609.22235v1 Announce Type: new Abstract: While multi-agent systems based on large language models (LLMs) have shown promise in automating the progressive workflow of academic research, extendin
arXiv:2609.23268v1 Announce Type: new Abstract: Blind image deconvolution (BID) is a prominent research topic in the field of imaging sciences, given its significant practical applications. Most exist
arXiv:2609.23387v1 Announce Type: new Abstract: Before a machine learning model can learn a thermodynamic equation of state, it must discover what its measurements represent: which channels scale with
arXiv:2609.22884v1 Announce Type: new Abstract: Long-context inference has become a defining capability of large language models, but exact dense attention remains costly due to its quadratic scaling
arXiv:2604.02103v3 Announce Type: replace Abstract: Realistic online handwriting depends not only on individual character shapes, but also on how a writer connects, spaces, and aligns adjacent charact
arXiv:2609.24769v1 Announce Type: new Abstract: Brain metastases are the most common intracranial malignancy, occurring in roughly 30% of patients with primary solid tumors and carrying a median survi
arXiv:2609.22282v1 Announce Type: new Abstract: Reconstructing visual stimuli from electroencephalography (EEG) is difficult because scalp measurements have high temporal but limited spatial resolutio
arXiv:2609.23026v1 Announce Type: new Abstract: Brain lesion segmentation is a fundamental task in medical image analysis, playing a critical role in diagnosis, treatment planning, and longitudinal di
arXiv:2510.17904v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are widely used because they process structures, syntax and code well, but this same ability also makes them para
arXiv:2609.24525v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have demonstrated remarkable generalization in robotic manipulation via large-scale multimodal pretraining. However,
arXiv:2609.24088v1 Announce Type: new Abstract: In latent generative models, reconstruction quality is often assumed to correlate with generative performance. However, reconstruction FID (rFID) can ex
arXiv:2609.23056v1 Announce Type: new Abstract: Agentic retrieval-augmented generation (RAG) enables language models to adapt retrieval based on previously retrieved evidence, but it remains unclear w
Amazon Bedrock has released OpenAI’s GPT‑6 Sol and GPT‑6 Luna as generally available services, offering distinct capabilities for advanced reasoning/coding (Sol) and high‑volume repeatable tasks (Luna
arXiv:2511.04919v3 Announce Type: replace Abstract: Processing long documents with large language models (LLMs) is expensive: a single query over a 100K-token document can cost from tens of cents to o
arXiv:2609.22807v1 Announce Type: new Abstract: Implicit Neural Representation (INR) leverages neural networks to represent discrete signals such as images as continuous ones, where the network weight
arXiv:2609.24052v1 Announce Type: new Abstract: Crash datasets that carry an investigator narrative hold information the coded fields omit. Coding those narratives at scale has been blocked by three o
arXiv:2506.12576v3 Announce Type: replace Abstract: Sparse autoencoders (SAEs) can enable inference-time topic steering by modifying latent feature activations, but existing steering methods often fai
arXiv:2609.22252v1 Announce Type: new Abstract: We present CALM, a reproducible hybrid framework that integrates an optional large language model (LLM) activity planner with calibrated stochastic choi
arXiv:2401.08038v2 Announce Type: replace Abstract: A significant challenge to training accurate deep learning models on privacy policies is the cost and difficulty of obtaining a large and comprehens
arXiv:2609.22253v1 Announce Type: cross Abstract: Model merging has emerged as a promising paradigm for integrating multiple task-specific capabilities into a single large language model. However, exi
arXiv:2609.22222v1 Announce Type: cross Abstract: Large language models can generate executable data-analysis code, but successful execution is not equivalent to a valid official-statistics result. Th
arXiv:2609.24403v1 Announce Type: new Abstract: Biological visual systems achieve continuous, low-latency motion perception by processing sparse, asynchronous spiking signals, enabling real-time track
arXiv:2609.24264v1 Announce Type: new Abstract: Tool-use agent traces identify messages and API calls, but procedural analyses also need explicit units of action and inspectable links to their evidenc
arXiv:2609.24118v1 Announce Type: new Abstract: Vision-Language-Action (VLA) policies achieve strong performance in robotic manipulation but remain brittle once execution deviates from nominal traject
arXiv:2609.24841v1 Announce Type: new Abstract: Multi-robot systems have shown increasing viability in construction due to their ability to execute high-precision actions while reducing human exposure
arXiv:2609.24112v1 Announce Type: cross Abstract: Causal Bayesian Optimization (CBO) combines causal inference with Bayesian optimization to enable sample-efficient intervention selection in systems w
arXiv:2609.23219v1 Announce Type: new Abstract: Unobserved confounding is a fundamental challenge in causal inference from observational data. This article develops a mixture-learning perspective, vie
arXiv:2609.22260v1 Announce Type: cross Abstract: A large audio language model (LALM) attaches a speech front end to a text language model (LM) that is already safety-aligned. When such a model refuse
arXiv:2609.23184v1 Announce Type: new Abstract: Embodied world models learn to predict future physical dynamics from visual observations and control signals, where physical knowledge is implicitly ent
arXiv:2609.22866v1 Announce Type: new Abstract: We introduce Causilo, a tabular foundation model (TFM) that combines frontier predictive performance with exceptionally fast inference. On TabArena, Cau
arXiv:2603.15309v2 Announce Type: replace Abstract: Solving problems through tool use under explicit constraints constitutes a highly challenging yet unavoidable scenario for large language models (LL
arXiv:2609.23492v1 Announce Type: new Abstract: Perception for embodied agents is video-based, often multi-view (ego, exo, or both), and inherently continual, with simultaneous task and viewpoint shif
arXiv:2609.22594v1 Announce Type: new Abstract: Autonomous underwater vehicles (AUVs) are a promising alternative to divers for scalable collection of natural ocean ecology data. However, these robots
arXiv:2609.22247v1 Announce Type: new Abstract: Search agents are usually trained under a single harness. But once an agent is deployed in a real application, its harness is frequently updated (e.g.,
arXiv:2609.24210v1 Announce Type: new Abstract: Building strong chart-to-code systems increasingly relies on reinforcement learning, whose effectiveness depends critically on the quality of the reward
arXiv:2609.22248v1 Announce Type: new Abstract: Systematic Literature Reviews (SLRs) are essential for evidence-based research but remain time-consuming, requiring researchers to manage large volumes
arXiv:2609.23231v1 Announce Type: new Abstract: Cross-lingual information retrieval (CLIR) is increasingly important in multi-national industries, where critical technical evidence may exist in a diff
arXiv:2609.22274v1 Announce Type: new Abstract: Recent advances in humanoid robotics have produced diverse skills through reinforcement learning, motion imitation, and generative modeling. Yet these c
arXiv:2609.23178v1 Announce Type: new Abstract: Language models are appealing tools for research on the past. But to trust the evidence a model provides, researchers need to know whether its responses
arXiv:2512.04723v2 Announce Type: cross Abstract: Human Action Recognition using WiFi Channel State Information (CSI) has emerged as an attractive alternative to vision-based methods due to its ubiqui
arXiv:2609.23892v1 Announce Type: new Abstract: Mechanistic interpretability defines features as the fundamental units of a neural network and circuits as the weighted subgraphs that carry out its com