Knowledge catalogue
arXiv:2606.00543v1 Announce Type: new Abstract: In Vision-Language Models (VLMs), high-resolution images produce a large number of visual tokens, resulting in high computational costs and KV-cache ove
arXiv:2606.01884v1 Announce Type: new Abstract: Practical non-invasive Brain-Computer Interface (BCI) systems require EEG decoders with strong cross-subject generalization and minimal calibration. How
arXiv:2606.02418v1 Announce Type: cross Abstract: Quantum LDPC code discovery requires searching large algebraic design spaces while reliably certifying the parameters and equivalence classes of any c
arXiv:2606.01271v1 Announce Type: new Abstract: The rapid growth of the satellite industry has driven a significant increase in geospatial data acquisition, highlighting a critical bottleneck: the sev
arXiv:2606.00795v1 Announce Type: cross Abstract: Metamodels for discrete-event simulations approximate the behavior of simulation models without running expensive simulations. Prior work introduced m
arXiv:2606.01964v1 Announce Type: new Abstract: The way our eyes move while reading provides valuable insights into both the reader's cognitive processes and the properties of the text. In particular,
arXiv:2603.23485v2 Announce Type: replace-cross Abstract: Standard evaluation practices assume that large language model (LLM) outputs are stable when prompts are embedded in contextually equivalent d
arXiv:2604.03893v2 Announce Type: replace Abstract: Current multimodal benchmarks for scientific reasoning primarily evaluate local information extraction -- models recognize symbols and values and th
arXiv:2606.01220v1 Announce Type: cross Abstract: Generating molecules that simultaneously satisfy drug-like properties and conform to the 3D structure of a target protein is a core challenge in struc
arXiv:2602.23197v2 Announce Type: replace Abstract: Transformer-based large language models exhibit in-context learning, enabling adaptation to downstream tasks via few-shot prompting with demonstrati
First technical Deepdive on M3 on the internet😎 MiniMax-M3 combines 1M context, native multimodality, and MiniMax Sparse Attention. The next layer is serving it efficiently: KV-block-major sparse atte
arXiv:2606.01352v1 Announce Type: new Abstract: Watch time has emerged as a pivotal metric for optimizing deep user engagement in short-video recommender systems. However, current methods of watch tim
arXiv:2510.09222v3 Announce Type: replace Abstract: Flow Matching (FM) has shown remarkable ability in modeling complex distributions and achieves strong performance in offline imitation learning for
arXiv:2606.01549v1 Announce Type: new Abstract: AI-based semantic and instance segmentation of terrestrial and drone LiDAR point clouds is emerging as a transformative approach for converting the comp
arXiv:2505.18492v5 Announce Type: replace Abstract: Mathematical competition problems fall into two broad types: theorem proving, which asks for a proof of a given statement, and answer construction,
arXiv:2606.02559v1 Announce Type: cross Abstract: Post-training compression of Large Language Models (LLMs) removes entire architectural components, either deleting them or replacing them with fitted
arXiv:2603.04828v2 Announce Type: replace Abstract: Pre-training data detection for LLMs is essential for addressing copyright concerns and mitigating benchmark contamination. Existing methods mainly
arXiv:2606.01008v1 Announce Type: cross Abstract: We present a benchmark for evaluating AI models and agents on real-world formal software verification tasks. We first scrape 11,039 property-based tes
arXiv:2606.02436v1 Announce Type: new Abstract: Video world models aim to simulate controllable visual environments, but long-horizon rollouts depend on what the model remembers after observations lea
arXiv:2606.01621v1 Announce Type: new Abstract: Vision-language models (VLMs) have become a common foundation for vision-and-language navigation in continuous environments (VLN-CE). Yet most VLM-based
arXiv:2601.13574v2 Announce Type: replace Abstract: Reconstructing the three-dimensional (3D) geometry of object surfaces is essential for robot perception, yet vision-based approaches degrade under l
Flux 2 Klein, the smaller quantized version of the Flux 2 image generation model, exhibits noticeable quality loss through VAE decoding artifacts that manifest as visual degradation in smooth gradient
arXiv:2606.02573v1 Announce Type: new Abstract: In this paper, we present HumanNOVA, a photorealistic, universal, and rapid model for generating 3D human avatars from a single RGB image. Achieving bot
arXiv:2602.11554v3 Announce Type: replace-cross Abstract: How far can 3D object detection go using 4D radar alone? Despite offering weather-robust and velocity-aware sensing for autonomous perception,
arXiv:2512.07192v2 Announce Type: replace Abstract: Vector Quantization (VQ) based generative image compression has achieved remarkable perceptual quality. However, existing VQ codecs suffer from two
arXiv:2606.00872v1 Announce Type: new Abstract: AI-generated image detection is a moving-target problem: detectors trained on one generator often fail when a new generator appears, and only a few labe
arXiv:2603.02650v2 Announce Type: replace-cross Abstract: Diffusion planners are a strong approach for offline reinforcement learning, but they can fail when value-guided selection favours trajectorie
arXiv:2606.00583v1 Announce Type: cross Abstract: Recent diffusion transformers have demonstrated strong image synthesis capabilities but remain inefficient to train due to weak alignment between gene
arXiv:2606.02161v1 Announce Type: cross Abstract: Video Large Language Models (Video-LLMs) achieve strong performance in video understanding, but their excessive visual tokens bring substantial comput
arXiv:2606.02453v1 Announce Type: cross Abstract: Despite the remarkable fidelity of generative models, they frequently suffer from mode collapse. Existing strategies for enhancing diversity predomina
arXiv:2606.00755v1 Announce Type: new Abstract: Reinforcement learning from verifiable rewards improves the reasoning ability of large language models, but often suffers from entropy collapse, in whic
arXiv:2606.00561v1 Announce Type: cross Abstract: Deep reinforcement learning (RL) offers a promising route to real-time power grid operation, yet large neural policies are costly to evaluate, hard to
arXiv:2509.24467v3 Announce Type: replace Abstract: Self-supervised learning (SSL) learns representations from massive unlabeled data, yet the resulting models typically operate as black boxes, necess
arXiv:2602.12972v2 Announce Type: replace-cross Abstract: In online advertising, marketing interventions such as coupons introduce significant confounding bias into Click-Through Rate (CTR) prediction
arXiv:2606.01282v1 Announce Type: new Abstract: Text-to-Image (TTI) systems are now everyday infrastructure for journalism, education, advertising, and public communication, and the demographic and cu
arXiv:2606.00266v1 Announce Type: cross Abstract: A long-standing challenge in distributed wireless systems is ensuring efficient and fair random channel access. Existing solutions often address speci
arXiv:2512.00470v4 Announce Type: replace Abstract: Diffusion models have demonstrated strong capabilities for modeling human-like driving behaviors in autonomous driving, but their iterative sampling
arXiv:2606.00991v1 Announce Type: new Abstract: Transportation systems management and operations (TSMO) increasingly depends on timely interpretation of heterogeneous data, from various sensor streams
arXiv:2606.00260v1 Announce Type: new Abstract: Human Activity Recognition (HAR) from ambient sensors enables smart-home applications such as health monitoring and assisted living. In realistic deploy
arXiv:2511.20639v3 Announce Type: replace-cross Abstract: Multi-agent systems (MAS) extend large language models (LLMs) from independent single-model reasoning to coordinative system-level intelligenc
arXiv:2606.01838v1 Announce Type: cross Abstract: Agentic language model systems alternate between two structurally distinct step types: structured tool calls (short, deterministic, low perplexity) an
arXiv:2606.00189v1 Announce Type: cross Abstract: Automated design and optimization of agentic LLM-based systems leads to sophisticated systems that substantially improve result quality over off-the-s
arXiv:2503.03137v3 Announce Type: replace Abstract: Constructive neural combinatorial optimization (NCO) offers a promising paradigm for solving vehicle routing problems (VRPs) by directly learning to
arXiv:2602.08689v2 Announce Type: replace Abstract: Diffusion models generate samples through an iterative denoising process guided by a pretrained neural network. Once the denoiser is fixed, the samp
arXiv:2603.00171v3 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) are shifting towards 'Thinking with Images' by actively exploring image details. While effective, lar
arXiv:2606.00666v1 Announce Type: cross Abstract: Transition metal complexes are central to catalysis, drug design, and materials science, with relevant properties strongly sensitive to their three-di
arXiv:2606.02463v1 Announce Type: cross Abstract: In 3D environments, Embodied Agents answer spatially relevant questions through reasoning from a mixture of modalities including natural language, RGB
arXiv:2606.01099v1 Announce Type: cross Abstract: Command understanding systems in smart home ecosystems can automate device control and substantially improve user experience. However, while they perf
MiniMax-M3 combines 1M context, native multimodality, and MiniMax Sparse Attention. The next layer is serving it efficiently: KV-block-major sparse attention, paged MSA decode, optimized index scoring
arXiv:2602.10623v2 Announce Type: replace-cross Abstract: Reward models learned from human preferences are central to aligning large language models (LLMs) via reinforcement learning from human feedba
arXiv:2606.01700v1 Announce Type: new Abstract: In this paper, a novel framework, MixerSENet, is introduced for hyperspectral image (HSI) classification, designed to address the challenges of computat
arXiv:2606.01993v1 Announce Type: cross Abstract: Abundant procedural knowledge on the Web holds great potential for helping agents solve long-horizon tasks. However, such knowledge is often multimoda
arXiv:2606.00288v1 Announce Type: new Abstract: Large language models are undergoing a transition from model technology to system technology. As developers use Codex, Claude Code, AutoGPT, and related
arXiv:2606.02105v1 Announce Type: new Abstract: End-to-End Autonomous Driving (E2E-AD) systems have largely converged on predicting intermediate trajectory waypoints, delegating final control to hand-
arXiv:2510.02528v2 Announce Type: replace Abstract: Large Multimodal Models (LMMs) demonstrate impressive in-context learning abilities from few multimodal demonstrations, yet the internal mechanisms
arXiv:2606.01442v1 Announce Type: cross Abstract: Network intrusion detection is a core component of modern cybersecurity infrastructure, yet the deep learning models that dominate the field are compu
arXiv:2603.27645v2 Announce Type: replace Abstract: Open-vocabulary change detection (OVCD) seeks to recognize arbitrary changes of interest by enabling generalization beyond a fixed set of predefined
arXiv:2606.00499v1 Announce Type: new Abstract: Video generation models are becoming a scalable form of world models, but they mainly generate plausible motion rather than proactively control or optim
arXiv:2606.01537v1 Announce Type: new Abstract: Clinical diagnosis often requires combining imaging with physiological measurements, yet deployed models typically operate on unimodal data. We present
arXiv:2606.01179v1 Announce Type: cross Abstract: Entropy production governs irreversibility and uncertainty in both physical and information-theoretic systems. While Physics-Informed Neural Networks