Knowledge catalogue
arXiv:2607.27348v1 Announce Type: new Abstract: Live2D is the dominant 2D character-animation format for anime characters and virtual avatars, representing each character as a stack of RGBA layers dri
arXiv:2607.27700v1 Announce Type: new Abstract: Large Vision-Language Models (VLMs) suffer from prohibitive inference overhead due to long sequences of visual tokens. However, existing visual token re
arXiv:2607.28146v1 Announce Type: new Abstract: As large language models (LLMs) are deployed as agents in high-stakes settings, such as medical and legal systems, understanding their deceptive capabil
arXiv:2607.27945v1 Announce Type: cross Abstract: Sequence models must decide what to write into memory and what to retain. In quantum and quantum-inspired sequence learning, nonlinear recurrent updat
arXiv:2603.12055v3 Announce Type: replace Abstract: Continual learning of pretrained vision-language models (VLMs) is prone to catastrophic forgetting, yet current approaches adapt to new tasks withou
arXiv:2607.28026v1 Announce Type: new Abstract: Recent advances in post-training Large Language Models (LLMs) increasingly rely on Reinforcement Learning with Verifiable Rewards (RLVR) or On-Policy Se
I'm an avid user of Deepseek v4 Flash via antirez's DS4 DwarfStar inference engine, and so when the new checkpoint dropped, the first thing I did was rent a cloud box and spin up a quantization for us
https://preview.redd.it/h7zv5tb3tmgh1.png?width=2854&format=png&auto=webp&s=507380e8f862c18f10f7c5c84da9e8d1c59139b0 Deepseek's new flash model is unexpectedly cheap and high-performing across useful
arXiv:2606.18997v2 Announce Type: replace Abstract: Uncovering the true informational architecture of real-world complex systems requires disentangling how their components uniquely store, redundantly
arXiv:2607.27248v1 Announce Type: cross Abstract: While large language models excel in reasoning, these generalists often lack knowledge for specialized scientific domains. Conversely, domain models~(
arXiv:2607.27891v1 Announce Type: cross Abstract: Temporal graph learning is commonly organized around the evolution of node states or the encoding of interaction histories. We study an underexplored,
arXiv:2607.28074v1 Announce Type: cross Abstract: Computer-use agents learn from what their actions change, so training one needs applications it can act on, break and reset. The applications that mat
arXiv:2607.27755v1 Announce Type: new Abstract: We address the problem of recovering the full-body mesh from only the head pose. This task has become essential for various applications based on head-m
arXiv:2603.05950v2 Announce Type: replace Abstract: Visual token reduction is critical for accelerating Vision-Language Models (VLMs), since visual inputs are represented as token sequences that intro
arXiv:2607.28582v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) is a promising approach to improve reasoning language models, but it remains brittle in practice: making it work reli
arXiv:2607.27290v1 Announce Type: new Abstract: Modern telecommunication, cloud, and microservice systems emit correlated alarm cascades when components fail. Root cause analysis (RCA) aims to identif
arXiv:2607.26367v1 Announce Type: new Abstract: An important skill in theoretical physics is to recognize when a new problem can be transformed into a known model. We study this skill as an AI-agent t
arXiv:2607.28319v1 Announce Type: new Abstract: This work presents Fairness Pruning, a lightweight structural intervention method designed for the management and future mitigation of demographic bias
arXiv:2607.28225v1 Announce Type: new Abstract: Agentic vision-language models (VLMs), which interleave textual reasoning with explicit tool calls such as cropping and code-based image manipulation, h
arXiv:2607.16387v2 Announce Type: replace-cross Abstract: An agent system's execution traces record how it fails, and procedures that improve such a system without changing model weights (trajectory s
arXiv:2607.28571v1 Announce Type: new Abstract: Operational Earth observation increasingly calls for answering queries such as ``find the image pairs where a new building appeared.'' This means search
arXiv:2508.02092v3 Announce Type: replace-cross Abstract: Large language models represent significant investments in computation, data, and engineering expertise, making them extraordinarily valuable
arXiv:2607.27995v1 Announce Type: cross Abstract: Adversarial training has emerged as a powerful approach for protecting models against adversarial attacks in a broad range of real-world applications.
arXiv:2607.28397v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) over knowledge graphs requires retrievers that can effectively capture both graph structure and semantic informat
arXiv:2607.26181v1 Announce Type: new Abstract: Functional verification dominates integrated circuit (IC) front-end engineering effort, and a single missed bug that escapes to silicon can trigger a co
arXiv:2607.27766v1 Announce Type: new Abstract: On-device in-context learning (ICL) relies on pre-inference retrieval to select demonstrations for useful context before downstream model inference. Thi
arXiv:2607.28456v1 Announce Type: cross Abstract: Solving large, sparse linear systems is a core task in scientific computing, and efficient iterative solvers rely critically on effective and robust p
arXiv:2607.28537v1 Announce Type: cross Abstract: Metallic magnets exhibit complex spin dynamics governed by electronically generated interactions. Predictive simulations of such dynamics typically re
arXiv:2607.26160v1 Announce Type: new Abstract: Clinical practice guidelines (CPGs) encode diagnostic criteria, but LLM systems typically retrieve guideline text or absorb it through training rather t
arXiv:2607.28394v1 Announce Type: new Abstract: Hand-object interaction (HOI) modeling remains challenging because it requires joint reasoning about hand articulation, object geometry, contact, semant
arXiv:2607.28301v1 Announce Type: new Abstract: Supervised fine-tuning (SFT) can equip large language models (LLMs) with domain knowledge for high-performance computing (HPC) tasks such as data race d
arXiv:2607.27652v1 Announce Type: new Abstract: Reinforcement learning (RL) search agents commonly model retrieval as free-form natural-language query generation and optimize multi-turn interactions u
arXiv:2607.27379v1 Announce Type: new Abstract: High-quality, diverse data are vital for large language models (LLMs) but remain scarce and costly. Data synthesis is a viable alternative and succeeds
arXiv:2607.28476v1 Announce Type: new Abstract: Early detection of mental health disorders is often limited by the lack of specialized resources in Spanish and the difficulty of analyzing long histori
'Intelligence too cheap to meter' battle is on! Given that DeepSeek-V4-Flash-Preview is already great for agentic tasks, there is no doubt this new checkpoint must be an absolute beast. 20+ point jump
arXiv:2607.28608v1 Announce Type: new Abstract: Clinical risk models routinely achieve strong aggregate performance while producing materially different error rates across patient subgroups. Audit pip
arXiv:2607.27952v1 Announce Type: new Abstract: Multimodal foundation models are reshaping edge-cloud visual intelligence from task-specific feature pipelines into token-based interfaces, where edge d
arXiv:2607.27529v1 Announce Type: new Abstract: Discrete diffusion and flow-matching models denoise a sequence over many steps, but to keep each step cheap, they factorize the transition across positi
arXiv:2607.27807v1 Announce Type: new Abstract: This paper studies learning-augmented and randomized online aggregation with delays on a line metric. We consider advice given as online suggested servi
arXiv:2607.28628v1 Announce Type: cross Abstract: Dualities play an important role in establishing both microscopic and emergent phenomena in a wide range of physical systems. In practice, though, it
arXiv:2607.28374v1 Announce Type: new Abstract: Multimodal agents for visual question answering increasingly operate as multi-step trajectories that interleave perception, retrieval, and reasoning, ye
arXiv:2607.28449v1 Announce Type: new Abstract: On-policy distillation (OPD) provides dense token-level supervision from a teacher, but its effectiveness can depend on teacher consistency, meaning tha
arXiv:2607.27704v1 Announce Type: cross Abstract: As large language models (LLMs) continue to demonstrate exceptional capabilities across various domains, the challenge of achieving energy-efficient a
arXiv:2603.10913v3 Announce Type: replace Abstract: Fine-tuning LLM-based text embedders via contrastive learning maps inputs and outputs into a new representational space, discarding the LLM's output
arXiv:2607.28135v1 Announce Type: new Abstract: Machine learning for combinatorial optimization typically relies on neural constructors trained via reinforcement learning on large offline datasets for
arXiv:2607.27787v1 Announce Type: new Abstract: Reinforcement learning from verifiable rewards (RLVR) for mathematical reasoning suffers from a structural blind spot: on 'cliff' prompts-those on which
arXiv:2607.17751v2 Announce Type: cross Abstract: We present MagicSelector, a joint optimization framework integrating Counterfactual task decomposition, Progressive reranking, and Dynamic Top-K, desi
arXiv:2607.27295v1 Announce Type: cross Abstract: The rational design of photocatalysts for environmental remediation and CO2 conversion remains limited by the high computational cost and sparse exper
arXiv:2607.27620v1 Announce Type: new Abstract: Deep learning has shown strong potential in medical image analysis, but most existing methods rely on large-scale annotations and a closed-world assumpt
arXiv:2607.27506v1 Announce Type: new Abstract: Language and embedding models used in RAG systems are conventionally assumed to require large-scale pretraining and explicit grounding supervision. We p
arXiv:2607.28277v1 Announce Type: new Abstract: Hyperspectral imaging is widely used in remote sensing and engineering. Therefore, research on its classification methods is crucial. While CNN and Tran
New research from Microsoft. This one is on training computer-use agents at scale. Recent pipelines generate synthetic environments in bulk, which moved the bottleneck from how many exist to what is i
arXiv:2603.16140v2 Announce Type: replace Abstract: Reinforcement learning with verifiable rewards (RLVR) has driven recent capability advances of large language models across various domains. Recent
arXiv:2607.27566v1 Announce Type: new Abstract: Multi-frame medical VQA appears to reward increasingly complex adaptation: controller-style inference, localization-aware reranking, static hard-negativ
arXiv:2607.28080v1 Announce Type: cross Abstract: We extend a recently introduced Entropy-Optimal Manifold Clustering (EOMC) to allow for a joint simultaneous identification of subsets and subspaces o
This post was not written by a clanker. Hey guys, I'm a comp sci major who wanted to introduce a cool project I built for quantizing models to ternary (1.58 bit) with as minimal of loss as possible, a
arXiv:2607.28437v1 Announce Type: new Abstract: Molecular optimization is commonly performed under a limited oracle budget, which makes deciding what to evaluate as important as deciding what to gener
arXiv:2607.28624v1 Announce Type: new Abstract: We introduce PhiZero, a physical world model built around physical language, a compact discrete representation of world-state transitions. Existing phys
arXiv:2607.27258v1 Announce Type: cross Abstract: Plant biosynthetic gene clusters (BGCs) encode specialized-metabolite pathways, yet curated plant BGC labels remain scarce, hindering supervised disco
arXiv:2607.23377v1 Announce Type: cross Abstract: The largest machine learning models in particle physics are also the most expensive to train, yet the return on scaling a given architecture cannot be