Knowledge catalogue
arXiv:2607.28879v1 Announce Type: cross Abstract: Similarity search over sparse set-valued data is often dominated by frequent background attributes because classical measures such as Jaccard, cosine,
arXiv:2607.29622v1 Announce Type: cross Abstract: Visual imitation learning enables robots to acquire visuomotor skills directly from images, yet RGB observations lack explicit geometric cues, making
arXiv:2607.28995v1 Announce Type: new Abstract: Accurate plant leaf modeling is fundamental to downstream tasks such as plant growth monitoring, and phenotyping for yield estimation. Autonomous roboti
arXiv:2607.28688v1 Announce Type: cross Abstract: We analyze Reflected UAS routing for heterogeneous multi-server queues at fixed parameters under subcritical load. The deterministic surrogate is a re
Hey there! So today we're releasing SupraBrain-50M, a hybrid language model that combines Gated DeltaNet linear recurrence with Sliding-Window Attention and Surprise-Gated update mechanisms to deliver
arXiv:2607.29412v1 Announce Type: new Abstract: Despite remarkable progress in vision-language generation, Vision-Language Models (VLMs) remain prone to hallucinations, producing content that is incon
arXiv:2607.29209v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) broadcasts a single response-level reward to every token, while on-policy distillation (OPD) sco
arXiv:2607.29569v1 Announce Type: new Abstract: This article presents a modular inference framework that integrates Flow Matching generative models with formal Control Barrier Function (CBF) safety gu
arXiv:2607.28969v1 Announce Type: new Abstract: Although Large Language Models (LLMs) have demonstrated promising safety performance, extending them to Multimodal Large Language Models (MLLMs) exposes
arXiv:2607.29033v1 Announce Type: new Abstract: Existing methods for adapting 2D foundation models such as SAM to 3D volumes either process slices independently---ignoring inter-slice context---or req
arXiv:2607.29679v1 Announce Type: new Abstract: We study empirical scaling properties for text conditioning in visual generation. Such properties have rarely been measured because diffusion loss does
arXiv:2607.28990v1 Announce Type: new Abstract: Large language model agents have shown promising capabilities in data-driven scientific discovery tasks, where an agent interacts with an execution envi
arXiv:2607.28693v1 Announce Type: cross Abstract: Industrial NILM remains challenging because measurement noise and widespread concurrent machine operation reduce the generalization of models tuned on
arXiv:2607.29347v1 Announce Type: cross Abstract: Modern neuroscience relies on integrating multi-scale, multimodal datasets to uncover the neural principles underlying intelligence. However, analytic
arXiv:2607.28777v1 Announce Type: new Abstract: Agent skills provide frozen large language model (LLM) agents with reusable procedural guidance, and recent work shows that such skills can be optimized
arXiv:2606.16639v2 Announce Type: replace Abstract: Multimodal learning exploits complementary information across heterogeneous modalities. The informativeness of each modality can vary widely across
arXiv:2506.13862v2 Announce Type: replace-cross Abstract: In Reinforcement Learning (RL), regularization with a Kullback-Leibler divergence that penalizes large deviations between successive policies
arXiv:2607.29397v1 Announce Type: new Abstract: Deploying large language models in realistic server environments poses challenges, as the system needs to provide high-quality responses with low latenc
arXiv:2607.28657v1 Announce Type: new Abstract: Large Language Models (LLMs) often require carefully crafted prompts to unlock their full potential, which can be a barrier for non-expert users. This w
arXiv:2607.29482v1 Announce Type: new Abstract: By relying on independent couplings from uninformative Gaussian priors, standard diffusion and flow matching models are forced to learn complex, high-co
arXiv:2607.29459v1 Announce Type: cross Abstract: Large-scale multivariate time series from heterogeneous IoT sensors demand accurate long-term forecasting for resource scheduling and predictive maint
arXiv:2607.29601v1 Announce Type: new Abstract: Parameter-Efficient Fine-Tuning (PEFT) commonly adapts large language models using a single shared Low-Rank Adapter (LoRA). This shared optimization spa
arXiv:2607.28642v1 Announce Type: new Abstract: Long chain-of-thought reasoning improves performance on complex problems, but it also introduces redundancy accumulation, context overflow, and error an
arXiv:2607.29254v1 Announce Type: new Abstract: AI agents extend large language models (LLMs) with external tools, enabling them to perform complex tasks and translate model outputs into consequential
arXiv:2607.28896v1 Announce Type: cross Abstract: Unified audio models capable of audio understanding, audio generation and, increasingly, audio editing are proliferating rapidly. Yet a basic question
arXiv:2607.29567v1 Announce Type: new Abstract: Manipulating transparent laboratory glassware that contains liquid is inherently safety-critical: even small geometric errors can cause unstable grasps
arXiv:2607.29287v1 Announce Type: cross Abstract: Multi-domain machine translation (MDMT) poses a unique challenge due to varying levels of linguistic complexity across domains. Inspired by human tran
arXiv:2607.29145v1 Announce Type: cross Abstract: Quantum software engineering is an emerging research field focusing on efficiently embedding the quantum programming paradigm into existing software e
arXiv:2607.29200v1 Announce Type: new Abstract: Ultrasound imaging has become increasingly widespread in clinical practice due to its portability, low cost and real-time capability, making ultrasound
arXiv:2607.28769v1 Announce Type: new Abstract: Security-critical biometric and forensic applications require accurate predictions and reliable confidence estimates, particularly under distribution sh
arXiv:2607.29370v1 Announce Type: new Abstract: Zero-shot anomaly detection (ZSAD) aims to detect and localize anomalies in unseen categories without access to target-specific training data. Although
arXiv:2607.29613v1 Announce Type: cross Abstract: Reinforcement learning (RL) post-training of Vision-Language-Action (VLA) models has shown strong promise for robotic manipulation. Among RL methods,
arXiv:2607.29463v1 Announce Type: new Abstract: Implicit Neural Representations (INRs) encode signals as the weights of a coordinate-based neural network and have recently been proposed as an alternat
arXiv:2607.29090v1 Announce Type: new Abstract: Postoperative adverse events, including mortality and morbidity, remain a major global burden, many of which are preventable through early identificatio
arXiv:2603.09161v2 Announce Type: replace-cross Abstract: Learning effective netlist representations is fundamentally constrained by the scarcity of labeled datasets, as real designs are protected by
I maintain xberg, an open-source (MIT) document extraction engine, and v1 is out. Sharing here because a common piece of a local Ollama RAG setup is 'get clean text out of my PDFs/Office files/images,
You probably used @FireworksAI_HQ this week. The cool part is that you just did not know you did. 🎆 Open-source models are free, sure... but the hard part is tailoring them so they perform best on you
arXiv:2607.29377v1 Announce Type: new Abstract: LLM agents need memory to act consistently over long interactions, yet many systems use additional LLM calls to operate that memory. Generating intermed
TL;DR: I spent 9 days developing a new quantization method for MLX models and measured 18 variants against each other on a single M5 Max MacBook Pro (128 GB). The result is the best-measuring MLX quan
audio.cpp 0.5 is out :) The most fun new model in 0.5 is DramaBox. It is closer to prompt-directed voice acting. DramaBox is built on the LTX-2.3 audio architecture, and prompts can control emotion, d
The biggest issue with preview was its inability to follow rules prompts and skills. It seems like no matter what you do it ignores them. I've tried first person and second person. I've tried Chinese
For anyone interested, here are the llama-bench results on 3 bit K_XL quantization. I think this could be pushed further but no luck so far. CURRENT RESULTS: full moe offloading Prefill suffers 116 --
A few people asked for this after the bandwidth thread, so here it is on its own instead of buried in a comment. The dense rule was simple: every token reads every weight, so tokens/sec ≈ bandwidth ÷
If you maintain an AGENTS.md or a CLAUDE.md, this is worth a read. (bookmark it) 288 gold-test evaluated runs across Claude Code and Codex, 17 real tasks from 3 repositories, with context-injection st
arXiv:2607.26520v1 Announce Type: cross Abstract: Conversational AI agents commonly lack persistent memory across sessions. The obvious fixes like injecting full chat histories into the context window
arXiv:2607.28625v1 Announce Type: new Abstract: Embodied intelligence faces a fundamental data bottleneck. Models must capture how first-person perception, whole-body motion, dexterous manipulation, o
arXiv:2512.02653v2 Announce Type: replace Abstract: Multi-view learning integrates diverse representations of the same instances and can improve performance when interactions across views are effectiv
arXiv:2607.27130v1 Announce Type: new Abstract: Ontology matching (OM) has traditionally been formulated as either equivalence discovery or subsumption matching. The existing OM systems identify only
arXiv:2607.28528v1 Announce Type: new Abstract: The rapid growth of large language models (LLMs) has resurrected age-old questions in sociolinguistics and world Englishes, such as who decides what cou
arXiv:2607.27705v1 Announce Type: cross Abstract: Large language models can contribute useful ideas to mathematical research, yet long-horizon proof attempts remain difficult to coordinate, evaluate,
arXiv:2607.28553v1 Announce Type: new Abstract: Predicting the 3D structures of atomic systems is fundamental to advancing material science and drug discovery. While flow-matching models (, FlowDPO) h
As shocking as the Kimi K3 release. Massive performance gain was just with post-training Model is 3x smaller than GLM 5.2 (10x smaller than K3) & works on a MacBook / Spark This is Q1 flagship (Opus 4
arXiv:2607.27611v1 Announce Type: new Abstract: Corporate annual reports contain weakly structured evidence about foreign-exchange risk management, derivative use, natural hedging, and explicit non-us
arXiv:2607.27600v1 Announce Type: new Abstract: Key-value (KV) cache management through compression and eviction strategies has emerged as an important research direction in recent years. Computationa
arXiv:2607.11623v3 Announce Type: replace Abstract: Real-world paired image dehazing remains challenging because haze degradation is spatially non-uniform, illumination-dependent, and physically ambig
arXiv:2205.06947v3 Announce Type: replace-cross Abstract: CT-based bronchial tree analysis is essential for diagnosing lung and airway diseases, yet automatic bronchus classification remains challengi
arXiv:2607.28595v1 Announce Type: new Abstract: The fundamental goal of agentic visual reasoning is to improve the success rate of multimodal large language models (MLLMs) on complex tasks, rather tha
arXiv:2607.27968v1 Announce Type: new Abstract: Machine unlearning seeks to selectively remove specific knowledge from trained language models without full retraining, a growing necessity under privac
arXiv:2607.27628v1 Announce Type: new Abstract: Low-light image enhancement (LLIE) methods involve tunable parameters that are typically fixed, often leading to performance degradation when applied ac
arXiv:2607.27366v1 Announce Type: new Abstract: While data synthesis for large language models (LLMs) is prevalent, it primarily targets domains with verifiable answers, overlooking open-ended humanit