Knowledge catalogue
arXiv:2609.12712v1 Announce Type: new Abstract: Relational table learning has recently emerged as an important research direction for modeling multiple tables connected through primary key-foreign key
arXiv:2609.12993v1 Announce Type: cross Abstract: We investigate the effect of pretrained T5 model scale and explicit motion features on pose-to-text Indian Sign Language Translation (SLT) for the WSL
arXiv:2609.12544v1 Announce Type: new Abstract: Clinical de-identification relies on accurately identifying personally identifiable information (PII). However, manually annotated datasets are costly t
arXiv:2609.12473v1 Announce Type: new Abstract: Scene-level point cloud understanding remains challenging due to diverse geometries and spatial layouts. While pre-trained 3D point cloud foundation mod
arXiv:2609.11956v1 Announce Type: new Abstract: Post-training with reinforcement learning (RL) is a critical phase in the development of code-generating large language models (LLMs), as it ensures adh
Now that the dust has settled a bit - here's a write-up on running Qwen3.8-Flash-Next (125B-A6B MoE + 51B n-gram table) on relatively middle-tier hardware (RTX 4070 12GB + 64GB DDR5-5600 + Gen4 NVMe o
arXiv:2609.12531v1 Announce Type: new Abstract: In streaming tasks, recurrent models can carry latent computation across time, allowing each update to build on representations produced earlier. This r
arXiv:2603.07357v3 Announce Type: replace Abstract: Latent generative models have emerged as powerful priors for solving inverse problems. These models typically represent a class of natural signals a
arXiv:2609.12397v1 Announce Type: new Abstract: Multi-modal image generation, particularly subject-driven customization, has garnered growing attention in recent years. Despite the rapid advancement o
arXiv:2609.12663v1 Announce Type: cross Abstract: Audio-based Multimodal Large Language Models (MLLMs) can generate detailed natural-language descriptions of complex acoustic scenes, yet it remains un
models : guard the expert FFN size fallback in nemotron-h against a zero divisor (#28779) The NextN/MTP tail loop derives the expert FFN size as n_ff/n_expert_used when expert_feed_forward_length give
from internlm: We introduce Intern-S2-397B, our most capable multimodal foundation model for scientific intelligence and long-horizon agents. Intern-S2-397B scales along three critical dimensions: pre
arXiv:2603.15976v2 Announce Type: replace Abstract: While LLMs have accelerated scientific code generation, comprehensively evaluating generated code remains challenging. Many benchmarks emphasize fun
hexagon: support for multi-device model split (aka row-split) (#28589) hex-row-split: add support for multi-device row spliting Co-authored-by: Max Krasnyansky maxk@qti.qualcomm.com hex-mdev: add work
I’ve been researching which models to sub to and I’m currently not subbed to anything. I’ve definitely searched here and other places for opinions but a lot of what I was reading wasn’t current or 6mo
I tried using deepseek v4.1 flash max subagents with astra extra high as an orchestrator. It was working perfectly with 1 until it suddenly stopped responding or doing work after 3 hours. Then trying
I have enabled the vision for the CIRU Strix UL4 quant of Qwen 3.8 flash next (others quants likely perform very similar) and tried it on a few things, then wanted to show my partner how great it work
arXiv:2609.11636v1 Announce Type: new Abstract: Domain practitioners understand their business constraints but may lack operations-research expertise or dedicated support. LLM-based optimization agent
The tweet reports on a widely‑cited incident involving OpenAI and Hugging Face, noting that analysts had to use the open‑source GLM 5.2 model to investigate an attack because OpenAI’s proprietary “saf
We’ve been watching both models closely on InferX, and something interesting is starting to show up. GLM-5.3 Flash might actually be outperforming DeepSeek V4.1 Flash for some real-world workloads. To
Same 44-token prompt: low = 202 output tokens in 15s, max = 4,955 in 35s, unset = 10,579 in 68s. I'm using it via claude code with this: CLAUDE_CODE_MAX_CONTEXT_TOKENS=1048576 ollama launch claude --m
arXiv:2609.10962v1 Announce Type: cross Abstract: Studies of the Model Context Protocol (MCP) server ecosystem draw their samples in ways that quietly select for servers that work: reference sets, pop
arXiv:2609.11698v1 Announce Type: new Abstract: This paper presents a coordinated trajectory generation and tracking control framework for a tail-sitter unmanned aerial vehicle (UAV), which does not r
arXiv:2609.10922v1 Announce Type: new Abstract: Auto-research agents have shown the potential to automate hypothesis generation, experiment execution, and iterative refinement. However, scaling this p
arXiv:2609.11302v1 Announce Type: new Abstract: Automatic Lyric Transcription (ALT) remains substantially more challenging than speech recognition due to melodic variability, rhythmic irregularity, an
arXiv:2609.11126v1 Announce Type: new Abstract: Verification and validation (V&V) of classification models is crucial to enable a wide range of sensor processing applications. Currently, the V&V proce
arXiv:2601.15397v3 Announce Type: replace-cross Abstract: The rapid emergence of new entities -- driven by cultural shifts, evolving trends, and personalized user data -- poses a significant challenge
arXiv:2509.24425v2 Announce Type: replace Abstract: The proliferation of Internet-of-Things (IoT) devices has led to an unprecedented volume of multivariate time series (MTS) data, requiring efficient
arXiv:2609.10943v1 Announce Type: new Abstract: The integration of large language models (LLMs) into video generation has enabled rapid text-to-video creation and improved visual quality. However, it
arXiv:2609.11141v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly used to generate structured outputs, but their reliability remains unclear when those outputs must satisfy
Anthropic reported that several users found ways to bypass its safeguards and use the Claude model for potentially bioweapons‑related research, including a researcher from an “unsupported region” who
arXiv:2609.10722v1 Announce Type: new Abstract: Structured extraction from Chinese military news supports intelligence analysis, decision-making, and knowledge base construction. However, existing res
arXiv:2603.21235v2 Announce Type: replace-cross Abstract: Nonrigid registration is conventionally divided into point set registration, which aligns sparse geometries, and image registration, which ali
arXiv:2609.10421v1 Announce Type: cross Abstract: Background: Emergency Department (ED) return visits are commonly reviewed for quality assurance, but are often limited (e.g., to revisits within 48-72
arXiv:2609.11240v1 Announce Type: new Abstract: The larval stage of Drosophila melanogaster is a compact model system for neuroscience whose genetic toolkit allows fluorescent markers to be expressed
arXiv:2609.10631v1 Announce Type: cross Abstract: A false data injection attack (FDIA) can change the estimated grid state while evading a residual-based bad data detector (BDD). Existing blind attack
I wanted to see how my fully local home voice assistant compared to the latest GPT Live, so I tested it using the same conversation used in their 'Improved Intelligence' demo. In this video they ask t
Hey ████, I think there is room for both. 1. Prototypes and other throw-away code can be treated as totally black box. If you’re going to throw it away anyway, and if the blast radius of it breaking i
arXiv:2609.10706v1 Announce Type: cross Abstract: Human video datasets have emerged as a compelling alternative to expensive real-robot data, offering rich diversity at scale. To bridge the human-to-r
arXiv:2609.09324v1 Announce Type: cross Abstract: Link Adaptation (LA) in 5G NR is inherently reactive, relying on channel measurements and HARQ feedback that may become quickly obsolete when the chan
arXiv:2609.11736v1 Announce Type: cross Abstract: We develop a quantum approach to spectral feature extraction from the density of states (DOS) of a problem-dependent Hamiltonian, and apply it to mach
arXiv:2609.09754v1 Announce Type: new Abstract: As large language models are increasingly deployed as tool-augmented legal agents, they introduce agentic hallucinations where tool-call and reasoning e
arXiv:2609.10545v1 Announce Type: cross Abstract: Federated Learning (FL) enables distributed model training without centralizing data but suffers from high communication overhead. To address this, we
arXiv:2609.10632v1 Announce Type: cross Abstract: Machine-learning systems are built almost exclusively on a few large Python-orchestrated frameworks, and they inherit those stacks' engineering costs:
arXiv:2609.11117v1 Announce Type: new Abstract: Reproducibility is essential to scientific progress, yet the growing volume and complexity of scientific publications make exhaustive manual verificatio
arXiv:2609.11101v1 Announce Type: new Abstract: Dispute mediation is essential for maintaining social harmony and resilience, yet developing skilled mediators is costly and time-consuming. Existing LL
arXiv:2502.17017v1 Announce Type: cross Abstract: Large language models (LLMs) have demonstrated impressive performance in various natural language processing tasks, yet their ability to perform multi
arXiv:2607.18116v2 Announce Type: replace-cross Abstract: Recent work leverages Large Language Models (LLMs) to generate executable code for pedagogical animations using libraries such as Manim. Howev
arXiv:2604.00280v2 Announce Type: replace-cross Abstract: Formal specifications play a central role in ensuring software reliability, yet automatically synthesizing high-quality specifications remains
I’ve been building 'Spomin', a router that replaces context with summaries directly in the KV cache. The goal is to keep long running sessions going without repeatedly stopping for full compaction and
arXiv:2506.08949v2 Announce Type: replace Abstract: In the era of information explosion, efficiently leveraging large-scale unlabeled data while minimizing the reliance on high-quality pixel-level ann
TLDR (written by AI because I can't be bothered to write short pieces for short attention spans. Original piece written with my own two thumbs): Today’s frontier models can’t “copy themselves like a v
arXiv:2609.11638v1 Announce Type: new Abstract: We present Vidu S2, which comprises Vidu S2-Avatar, a real-time interactive digital-character model, and Vidu S2-Editing, a real-time video editing mode
arXiv:2609.10767v1 Announce Type: cross Abstract: We develop an exact almost-sure learning theory for smooth parametric models trained by regularly weighted empirical risk minimization on long-range d
arXiv:2609.11772v1 Announce Type: cross Abstract: Cross-cultural understanding has become increasingly important in today's highly connected, cross-national world. The success of LLM-based technologie
arXiv:2609.11274v1 Announce Type: cross Abstract: Recently, large language model (LLM) based ASR models have achieved significant progress, yet they generally lack support for multi-speaker scenarios,
arXiv:2109.02355v2 Announce Type: replace-cross Abstract: The last decade of progress in machine learning (ML), especially the deep learning era, has raised a number of scientific questions that chall
arXiv:2609.06573v1 Announce Type: new Abstract: Recent studies report that automated red-teaming finds more vulnerabilities, at lower cost, than human red-teaming on standard AI safety benchmarks, and
arXiv:2609.10456v1 Announce Type: new Abstract: Nanoscale imaging of mammalian brains is critical for connectomics. X-ray laminography enables high-throughput imaging of extended, plate-like biologica
spec: fix failed to decode mtmd chunk with DFlash (#28587) speculative: fix failed to decode mtmd chunk with DFlash When using DFlash w/ vision models, the drafter memory fails to allocate new tokens