Knowledge catalogue
arXiv:2605.18553v1 Announce Type: cross Abstract: Recovering world space 4D motion of two interacting hands from egocentric video is a fundamental capability for supervising robot policy learning, whe
arXiv:2605.18603v1 Announce Type: new Abstract: Vision-Language Models (VLMs) deployed as situated agents in high-resolution visual environments require active perception -- the ability to dynamically
arXiv:2605.18656v1 Announce Type: cross Abstract: Federated Learning is a leading framework for training ML and AI models collaboratively across numerous user devices or databases. We study the trade-
arXiv:2605.17291v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) is widely used to improve reasoning in large language models, but rewards only final-answer correc
arXiv:2605.17672v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) achieve strong performance by generating long chains of thought (CoT), but often overthink, continuing to reason after a s
arXiv:2605.16470v1 Announce Type: cross Abstract: Adapting large language models (LLMs) to downstream tasks via full fine-tuning is increasingly impractical due to its computational and memory demands
arXiv:2605.17790v1 Announce Type: new Abstract: LLM-based equation discovery offers a promising route to recovering symbolic laws from data, but many systems still rely on generation-centered loops th
arXiv:2605.16353v1 Announce Type: cross Abstract: Continual Visual Instruction Tuning (CVIT) enables Multimodal Large Language Models to incrementally acquire new abilities. However, existing CVIT met
arXiv:2506.05442v2 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) offer a promising approach to end-to-end autonomous driving due to their human-like reasoning capabilities. Howe
arXiv:2605.17568v1 Announce Type: new Abstract: Multi-class event streams arise in numerous real-world applications, where uncovering structured, interpretable inter-event relationships, together with
arXiv:2511.19953v2 Announce Type: replace Abstract: Accurate nuclear instance segmentation is a pivotal task in computational pathology, supporting data-driven clinical insights and facilitating downs
arXiv:2502.13957v3 Announce Type: replace-cross Abstract: Large language models (LLMs) are transforming web search by shifting from document ranking to synthesizing answers, and are increasingly deplo
arXiv:2605.18745v1 Announce Type: cross Abstract: Diffusion-based generative models increasingly rely on inference-time guidance, adding a drift term or reweighting mixture of experts, to improve samp
arXiv:2605.17915v1 Announce Type: new Abstract: Surgical Video Question Answering (VideoQA) provides a promising paradigm for dynamic intraoperative interpretation, enabling real-time decision support
arXiv:2602.16473v2 Announce Type: replace Abstract: C-RASP is a simple programming language that was recently shown to capture concepts expressible by transformers. In this paper, we develop new algor
arXiv:2605.18383v1 Announce Type: new Abstract: We present TabH2O, a foundation model for tabular data that performs classification and regression in a single forward pass via in-context learning. Tab
arXiv:2605.17336v1 Announce Type: cross Abstract: Tactile sensing is a fundamental modality for embodied intelligence, offering unique and direct feedback on contact geometry, material properties, and
arXiv:2605.17577v1 Announce Type: new Abstract: Large-scale pre-trained Vision-Language models (VLMs), such as CLIP, exhibit strong zero-shot generalization, yet remain highly vulnerable to impercepti
arXiv:2605.17029v1 Announce Type: cross Abstract: Large language models (LLMs) have revolutionized automated code generation. One serious concern, however, is the so-called ``hallucination'', i.e., LL
arXiv:2605.16895v1 Announce Type: cross Abstract: End-to-end LLM trading agents have moved quickly from research curiosity to a small ecosystem of named systems, including FinCon, FinMem, TradingAgent
arXiv:2601.03425v2 Announce Type: replace-cross Abstract: Mixture of Experts models are widely assumed to achieve domain specialization through sparse routing. In this work, we question this assumptio
I put together these annotated slides from my five minute lightning talk at PyCon US 2026, using the latest iteration of my annotated presentation tool. # I presented this lightning talk at PyCon US 2
arXiv:2605.17087v1 Announce Type: new Abstract: Generative data augmentation with latent diffusion models is a promising strategy for addressing class imbalance in medical imaging, yet current approac
arXiv:2605.16644v1 Announce Type: cross Abstract: A central obstacle in nonlinear Bayesian filtering is representing the belief distribution. Moment-based filters address this by propagating polynomia
arXiv:2601.13992v2 Announce Type: replace-cross Abstract: Chain-of-Thought (CoT) reasoning empowers Large Language Models (LLMs) with remarkable capabilities but typically requires prohibitive paramet
this has probably been the most interesting project i've ever worked on. we created the best agent at finding problems with your agent. and we integrated it with the best observability platform to spi
arXiv:2605.18058v1 Announce Type: new Abstract: Arabic handwriting recognition (AHR) has made significant progress with deep learning models. AHR research has largely focused on performance, with secu
Today we release Contrastive Neuron Attribution (CNA), a method for steering LLM behavior by identifying and ablating sparse circuits in the MLP basis without training a sparse autoencoder, modifying
arXiv:2510.24701v3 Announce Type: replace-cross Abstract: We present Tongyi DeepResearch, an agentic large language model, which is specifically designed for long-horizon, deep information-seeking res
arXiv:2510.14466v3 Announce Type: replace-cross Abstract: Large language models (LLMs) continue to struggle with low-resource languages, primarily due to limited training data, translation noise, and
arXiv:2605.16879v1 Announce Type: new Abstract: With the rapid evolution of synthetic media, Image Manipulation Localization (IML) has emerged as a critical component in multimedia forensics for ensur
arXiv:2602.10503v2 Announce Type: replace Abstract: Pretrained on large-scale and diverse datasets, VLA models demonstrate strong generalization and adaptability as general-purpose robotic policies. H
arXiv:2601.20306v2 Announce Type: replace Abstract: All-in-one image restoration aims to address diverse degradation types using a single unified model. Existing methods typically rely on degradation
arXiv:2605.18163v1 Announce Type: new Abstract: Hallucination correction is not a one-direction problem. We show that intermediate layers are neither uniformly more truthful than final layers nor unif
arXiv:2602.12687v2 Announce Type: replace-cross Abstract: The core of knowledge distillation lies in transferring the teacher's rich 'dark knowledge'-subtle probabilistic patterns that reveal how clas
arXiv:2409.10102v2 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) has quickly grown into a pivotal paradigm in the development of Large Language Models (LLMs). Although ex
arXiv:2605.16638v1 Announce Type: new Abstract: Recent research has demonstrated that Universal Multimodal Embedding (UME) benefits significantly from Chain-of-Thought (CoT) reasoning. In this paradig
arXiv:2509.23986v2 Announce Type: replace Abstract: Scientific discovery is often slowed by the manual development of computational tools needed to analyze complex experimental data. Building such too
arXiv:2605.16690v1 Announce Type: new Abstract: Heterogeneous LoRA-rank methods address system heterogeneity in federated fine-tuning of foundation models by assigning client-specific ranks based on c
arXiv:2504.20734v4 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) has shown substantial promise in improving factual accuracy by grounding model responses with external kn
arXiv:2605.17976v1 Announce Type: new Abstract: Scientific discovery is increasingly constrained by costly experiments and limited resources, underscoring the need for efficient optimization in AI for
arXiv:2605.17748v1 Announce Type: new Abstract: In the field of Blind Image Quality Assessment (BIQA), accurately predicting the perceptual quality of authentically distorted images remains highly cha
arXiv:2510.13870v3 Announce Type: replace-cross Abstract: Diffusion Language Models (DLMs) have emerged as a promising alternative to Autoregressive Language Models, yet their inference strategies rem
arXiv:2605.16306v1 Announce Type: cross Abstract: In industrial design, N-sided hole filling is typically formulated as the construction of a single trimmed B-spline surface by minimizing a fairness e
arXiv:2605.17605v1 Announce Type: new Abstract: Modern generative modeling has grown into a broad collection of related but often separately implemented paradigms, including denoising diffusion models
arXiv:2605.17998v1 Announce Type: cross Abstract: As multi-agent systems move from short interactions to tool-using workflows with specialized roles and persistent state, completion becomes a runtime-
arXiv:2603.11075v2 Announce Type: replace-cross Abstract: As Very Large Scale Integration (VLSI) designs continue to scale in size and complexity, layout verification has become a central challenge in
arXiv:2605.16859v1 Announce Type: cross Abstract: 3D change detection from multi-view images is essential for urban monitoring, disaster assessment, and autonomous driving. However, existing methods p
arXiv:2605.16420v1 Announce Type: new Abstract: This paper addresses the problem of reconstructing missing or dropped frames in top-down drone video of autonomous surface vehicles performing structure
arXiv:2605.18192v1 Announce Type: new Abstract: Aerial-Ground Person Re-Identification (AGPReID) remains highly challenging due to drastic viewpoint variations between drones and fixed cameras. Existi
arXiv:2605.17815v1 Announce Type: cross Abstract: Efficient object manipulation strategies have significant impact in automation applications. In this work, the stack rearrangement in tabletop setting
arXiv:2605.18160v1 Announce Type: cross Abstract: In recent years, multimodal large language models (MLLMs) have achieved remarkable progress, primarily attributed to effective paradigms for integrati
arXiv:2605.18740v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) still struggle with fine-grained visual understanding, where answers often depend on small but decisive evide
arXiv:2605.17584v1 Announce Type: new Abstract: Unsupervised pixel-level video understanding remains challenging in real-world scenarios, where motion blur, occlusion, and fast object dynamics often c
arXiv:2605.17472v1 Announce Type: new Abstract: Pre-trained vision foundation models (VFMs) provide strong semantic representations, yet their patch-level features are inherently coarse, limiting thei
arXiv:2605.18029v1 Announce Type: new Abstract: Multimodal product retrieval (MPR) underpins checkout-free retail and automated inventory systems, yet it demands fine-grained SKU discrimination that s
arXiv:2605.17265v1 Announce Type: new Abstract: Accurate prediction of molecular properties underpins drug discovery and material design, yet even state-of-the-art models remain vulnerable to localize
arXiv:2601.17887v2 Announce Type: replace Abstract: Long-term memory enables large language model (LLM) agents to support personalized and sustained interactions. However, most work on personalized ag
arXiv:2605.16403v1 Announce Type: new Abstract: Despite rapid progress in video-capable MLLMs, we find that their apparent audio understanding in videos is often vision-driven: models rely on visual c
arXiv:2605.16602v1 Announce Type: cross Abstract: Touch plays a central role in how humans perceive and recognize materials through physical contact. Despite decades of research, the mechanisms by whi