Knowledge catalogue
Google DeepMind released Gemma 4 12B, an open AI model that brings multimodal capabilities to everyday laptops by processing text, images, and audio natively without separate encoders. Small enough to
arXiv:2606.03022v1 Announce Type: cross Abstract: Hallucination in Large Language Models (LLMs), characterized by the generation of content inconsistent with contextual facts or logical constraints --
Harvey just published a study showing a hybrid setup, open source GLM 5.1 as primary worker, routing to Opus 4.7 only when needed beats pure Opus 4.7 on quality and costs less. This is the multi-model
arXiv:2606.02600v1 Announce Type: cross Abstract: We study autoencoder and variational-autoencoder latent spaces through the lens of spin-glass theory. The paper has two components. First, we formaliz
arXiv:2506.13107v4 Announce Type: replace Abstract: Causal forests estimate how treatment effects vary across individuals, guiding personalized interventions in areas like marketing, operations, and p
arXiv:2606.03549v1 Announce Type: new Abstract: Hyperparameter optimization (HPO) for Random Forest faces a specific difficulty in tuning the number of trees: the predictive score typically improves m
arXiv:2606.03768v1 Announce Type: new Abstract: Extended chain-of-thought (CoT) traces improve LLM reasoning but incur substantial computational and memory costs. While existing CoT compression method
arXiv:2606.03179v1 Announce Type: new Abstract: Large Language Models (LLMs) rely on Knowledge Editing (KE) to maintain temporal validity, yet real-world knowledge is inherently n-ary. We demonstrate
arXiv:2606.03988v1 Announce Type: new Abstract: Vision language models (VLMs) excel at many tasks but still struggle with spatial reasoning when critical information is not directly observable. Many s
arXiv:2606.02662v1 Announce Type: cross Abstract: Machine learning has accelerated quantum chemistry but is hindered by the prohibitive cost of generating high fidelity training data. Multifidelity ma
In early May, the best superforecasters predicted that, by the end of the year, the longest METR 80% task horizons would reach 3-4 hours. In late May, Claude Mythos achieved that number. We also asked
arXiv:2606.03183v1 Announce Type: cross Abstract: Joint audio-video generation aims to synthesize realistic audio-video pairs that are both semantically aligned with text prompts and precisely synchro
arXiv:2602.06960v3 Announce Type: replace-cross Abstract: Large reasoning models achieve strong performance by scaling inference-time chain-of-thought, but this paradigm suffers from quadratic cost, c
arXiv:2606.02963v1 Announce Type: new Abstract: Production inference increasingly targets a heterogeneous mix of accelerators. Agentic pipelines interleave reasoning, tool calls, and multi-agent coord
arXiv:2602.20217v2 Announce Type: replace-cross Abstract: Self-speculative decoding (SSD) accelerates LLM inference by skipping layers to create an efficient draft model, yet existing methods often re
arXiv:2606.03539v1 Announce Type: new Abstract: Spatio-Temporal Video Grounding aims to localize object tubes based on textual queries. While recent methods have achieved remarkable success, they main
arXiv:2606.03458v1 Announce Type: new Abstract: Test-time scaling is a powerful approach to obtain better reasoning in large language models, but it becomes memory-bottlenecked during long-horizon dec
arXiv:2602.05031v2 Announce Type: replace Abstract: Planning with a learned model remains a key challenge in model-based reinforcement learning (RL). In decision-time planning, state representations a
arXiv:2606.02914v1 Announce Type: new Abstract: Background: Oral diseases affect nearly 3.5 billion people worldwide, yet the comparative clinical potential of large-scale AI models in dentistry remai
arXiv:2606.03437v1 Announce Type: new Abstract: Prior work has shown that instruction-tuned large language models (LLMs) are less well calibrated than their base pre-trained counterparts. However, lit
arXiv:2602.07075v5 Announce Type: replace-cross Abstract: Current chemical large language models (LLMs) predominantly rely on explicit Chain-of-Thought (CoT) to solve complex reasoning problems. Howev
arXiv:2606.03489v1 Announce Type: cross Abstract: While Large Language Models (LLMs) excel in code generation, they remain prone to replicating subtle yet critical vulnerabilities endemic to their tra
arXiv:2606.03310v1 Announce Type: cross Abstract: Understanding complex interactions between brain regions is critical for early neurodegenerative disease classification such as Alzheimer's Disease (A
arXiv:2606.02661v1 Announce Type: cross Abstract: Accurate precipitation nowcasting is vital for disaster mitigation, but deep learning methods face a key trade-off: regression models produce over-smo
arXiv:2606.03087v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) improves the ability of large language model, yet headline accuracy gains often conceal a hidden c
arXiv:2505.24037v3 Announce Type: replace Abstract: Sparse large language models (LLMs) offer an attractive direction toward efficient deployment, but adapting them to downstream tasks remains challen
arXiv:2606.03834v1 Announce Type: new Abstract: Flow matching has recently emerged as a powerful approach for imitation learning, enabling scalable, expressive, and multimodal motion policies. However
arXiv:2606.03794v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) have emerged as a powerful tool for wireless resource allocation that leverages the underlying graph structure of communica
arXiv:2606.02907v1 Announce Type: cross Abstract: Linear probing of large language model (LLM) hidden states is widely used to claim that models learn distinct representations for different reasoning
arXiv:2606.03365v1 Announce Type: new Abstract: Embedding models (KGEMs) constitute the main link prediction approach to complete knowledge graphs. Standard evaluation protocols emphasize rank-based m
arXiv:2606.03803v1 Announce Type: cross Abstract: We present LiveBand, a real-time system that generates high-fidelity music accompaniments to live audio input, respecting strict causal constraints. O
arXiv:2606.03402v1 Announce Type: new Abstract: Audio-driven human motion video generation aims to synthesize realistic and temporally coherent human animations from a single static image, with applic
arXiv:2606.02996v1 Announce Type: cross Abstract: Inertial odometry (IO) using only Inertial Measurement Units (IMUs) provides a lightweight solution for human motion tracking in augmented reality (AR
arXiv:2606.03243v1 Announce Type: new Abstract: Modern text-to-image models have achieved strong visual synthesis, yet remain unreliable when prompts require implicit visual constraints, relational re
arXiv:2606.02976v1 Announce Type: new Abstract: Long-context dialogue systems must decide both when to access memory and which parts of the interaction history are relevant. Existing approaches typica
arXiv:2606.03197v1 Announce Type: new Abstract: Memory is an indispensable capability for long-horizon LLM agents, enabling them to preserve and utilize information accumulated across extended interac
arXiv:2606.03290v1 Announce Type: cross Abstract: Graph Foundation Models (GFMs), built upon the Pre-training and Adaptation paradigm, have emerged as a research hotspot in graph learning. For GNN-bas
arXiv:2606.03470v1 Announce Type: new Abstract: We introduce Dual Face-Hair Retrieval (DFHR), a new mixed-modality dual-reference task in image retrieval where a query consists of a face image specify
arXiv:2606.02892v1 Announce Type: new Abstract: Breast cancer recurrence, a leading cause of long-term mortality among survivors, requires timely and accurate risk assessment to guide follow-up care a
arXiv:2606.03698v1 Announce Type: new Abstract: A central goal of large language model (LLM) research is to build agentic systems that can plan, act, and adapt through sustained interaction with dynam
arXiv:2606.03291v1 Announce Type: new Abstract: Large language models (LLMs) can memorize sensitive facts, motivating unlearning methods that remove targeted knowledge without costly retraining. Howev
arXiv:2606.03005v1 Announce Type: cross Abstract: Despite rapid progress, multimodal large language models (MLLMs) still fail on tasks that humans solve effortlessly, such as navigating a grid maze fr
arXiv:2606.02788v1 Announce Type: cross Abstract: Reconstructing the direction of incoming neutrinos in the IceCube Neutrino Observatory is an important problem in astrophysics. The public IceCube--Ne
Nice primer on post-training reasoning data. (bookmark it) This is one of the first primers to pull the scattered post-training reasoning-data literature into one place, synthesizing over 150 public s
arXiv:2512.19347v3 Announce Type: replace Abstract: Robot manipulation has increasingly adopted data-driven generative policy frameworks, yet the field faces a persistent trade-off: diffusion models s
arXiv:2602.07768v3 Announce Type: replace-cross Abstract: Distilling knowledge from large Vision-Language Models (VLMs) into lightweight networks is crucial yet challenging in Fine-Grained Visual Clas
arXiv:2606.03915v1 Announce Type: new Abstract: We propose PatchScene, a novel diffusion-based framework for large-scale LiDAR scene completion. Unlike existing methods that rely on global latent repr
arXiv:2606.02877v1 Announce Type: new Abstract: Integrating transcriptomics and histopathology can improve cancer risk modelling, yet practical use is constrained by the limited availability of RNA pr
arXiv:2606.03236v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have substantially advanced mobile agents, yet proactive mobile assistance remains challenging because agents m
arXiv:2606.03376v1 Announce Type: cross Abstract: Hallucination has recently garnered significant research attention in Large Vision-Language Models (LVLMs). Direct Preference Optimization (DPO) aims
arXiv:2602.05302v3 Announce Type: replace Abstract: We present an in-depth evaluation of LLMs' ability to negotiate, a central business task requiring strategic reasoning, theory of mind, and economic
arXiv:2409.08958v3 Announce Type: replace-cross Abstract: Physics-informed neural networks (PINNs) have emerged as a powerful deep learning approach for solving partial differential equations (PDEs) i
arXiv:2601.12247v3 Announce Type: replace-cross Abstract: Diffusion Language Models (DLMs) present a promising non-sequential paradigm for text generation, distinct from standard autoregressive (AR) a
arXiv:2606.02991v1 Announce Type: cross Abstract: We introduce TypewriterLM, a 7.24B History language model (LM) trained exclusively on English text predating 1913. Developing History LMs requires add
arXiv:2606.02831v1 Announce Type: new Abstract: Single-image reflection separation is fundamentally challenged by the entanglement of transmission and reflection layers under complex image formation p
arXiv:2604.07048v2 Announce Type: replace Abstract: Real-world image dehazing (RID) aims to remove haze-induced degradation from real scenes. This task remains challenging due to non-uniform haze dist
arXiv:2510.17149v3 Announce Type: replace Abstract: As large-scale multi-agent systems evolve, the communication protocol layer has become a critical yet under-evaluated factor shaping performance and
arXiv:2606.02754v1 Announce Type: new Abstract: Personalization is a crucial capability of modern language agents. However, current research primarily positions personalized agents as passive responde
arXiv:2512.10888v3 Announce Type: replace Abstract: Table extraction (TE) is a key challenge in document understanding. Traditional approaches detect tables first, then recognize their structure. Rece
arXiv:2606.03938v1 Announce Type: cross Abstract: Multi-epoch training is becoming the standard now that compute is growing faster than the supply of high-quality text. But pretraining a single model