Knowledge catalogue
Hello! We've been busy at Telperion with a lot of experimental research (more coming soon). Today, we're announcing the release of our latent attention variants of Qwen3.8-27B. Our latent attention va
arXiv:2610.18412v1 Announce Type: new Abstract: Prompt-based adaptation offers several ways to specialize a frozen language model, ranging from natural-language prompt optimization to learned continuo
arXiv:2610.16452v1 Announce Type: new Abstract: Explainable face forgery detection requires not only correct judgments but also forensic evidence supported by the input image. However, training cues a
arXiv:2610.14074v1 Announce Type: new Abstract: Large language models typically support different inference budgets through separate model sizes or fixed compute configurations. In multi-turn interact
arXiv:2502.04356v2 Announce Type: replace-cross Abstract: In response to the success of proprietary Large Language Models (LLMs), there is a growing interest in developing open, non-proprietary LLMs a
arXiv:2610.18808v1 Announce Type: cross Abstract: In cooperative Multi-Agent Reinforcement Learning (MARL), agents must learn to coordinate their actions to achieve shared objectives. A key indicator
arXiv:2610.16066v1 Announce Type: new Abstract: Detailed video captioning has become an essential semantic interface for multi-modal understanding and generation. While existing methods mainly target
arXiv:2610.14864v1 Announce Type: new Abstract: Action chunking improves temporal coherence in visuomotor imitation learning by jointly predicting sequences of future actions. However, many existing p
arXiv:2610.13982v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models have emerged as an effective paradigm for scaling large language models, yet their massive parameter footprint poses sev
arXiv:2610.16302v1 Announce Type: new Abstract: Video-based interactive world models aim to enable real-time, user-controllable environments. Yet most existing systems are trained and rolled out at a
arXiv:2610.14832v1 Announce Type: new Abstract: This paper presents a reproducibility study of ``Boosting the Visual Interpretability of CLIP via Adversarial Fine-Tuning'', published at ICLR 2025, whi
Reachy Mini is an open-source robot from Pollen Robotics and Hugging Face, run by a Raspberry Pi with 4 GB of RAM. We wanted it to do what a good host does: greet you by name the second time you walk
arXiv:2610.17623v1 Announce Type: new Abstract: Rubric-based reinforcement learning grades a response against many written criteria but collapses them into one reward, which discards the detail the ru
arXiv:2610.14921v1 Announce Type: new Abstract: A language model that keeps learning online must not slowly erode its own base capabilities. We ask which part of a modern LLM should absorb continual u
arXiv:2610.14474v1 Announce Type: new Abstract: Medication recommendations seek to deliver personalized drug combinations based on patients' clinical information, where ensuring transparent decision-m
arXiv:2604.01581v4 Announce Type: replace Abstract: Drone-view geo-localization (DVGL) typically assumes access to satellite imagery during task-specific development. We study a late-arriving-gallery
arXiv:2610.17080v1 Announce Type: new Abstract: Unified multimodal models (UMMs) provide an interface for interleaved text-image generation, where generated visual states can directly inform subsequen
arXiv:2610.17661v1 Announce Type: new Abstract: The rapid development of mobile imaging and social platforms has led to explosive growth in user-generated content images, making their systematic and c
arXiv:2610.18374v1 Announce Type: new Abstract: RGB-based category-level 9D pose estimation remains highly challenging because a monocular system must generalize across unseen object instances while j
arXiv:2610.17874v1 Announce Type: new Abstract: Discovering what drives an outcome from data is central to science and often requires deciding what is worth investigating before a specific hypothesis
arXiv:2610.14835v1 Announce Type: new Abstract: Branch-and-bound (BnB) solves mixed-integer linear programs by constructing and exploring a search tree. Node selection and branching are two recurrent
arXiv:2606.12956v2 Announce Type: replace Abstract: Long-horizon robot mobile manipulation requires continual reasoning about localization, environment changes, and task progress, all of which are cha
arXiv:2610.13996v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards improves mathematical reasoning when a final answer can be checked, but a correct answer does not certify
arXiv:2610.14601v1 Announce Type: new Abstract: In this work, we aim to develop an embodied MLLM agent that understands and solves embodied tasks by learning, abstracting, and reusing transferrable an
arXiv:2610.14651v1 Announce Type: new Abstract: The recent Segment Anything Model 3 (SAM3) extends powerful promptable segmentation from spatial cues to concepts, raising the prospect of a single foun
Luca Bertuzzi / Euronews: The EU Commission's AI Office launches formal AI Act probes into OpenAI and Anthropic over AI agent hacks; experts say the AI Act includes an R&D exemption — The EU is invest
arXiv:2610.15629v1 Announce Type: new Abstract: Choosing a mixed-precision configuration for large language model (LLM) serving trades speed against accuracy. Allocators that use average bit-width or
arXiv:2610.17065v1 Announce Type: new Abstract: Real-world tables are often heterogeneous, combining numerical features with free-form string columns. Table foundation models (TFMs) excel on numerical
arXiv:2610.18276v1 Announce Type: new Abstract: Infrared small target detection is often used in different civilian and military applications to detect static or moving targets in scenes like in groun
arXiv:2610.15038v1 Announce Type: new Abstract: Real-world Vision-Language Navigation (VLN) requires agents to act under partial observability, where map structure, semantic cues, and target locations
arXiv:2610.18789v1 Announce Type: new Abstract: Agentic remote sensing is evaluated on how many questions it can answer, whereas crisis response depends on whether its answers can be relied on and how
arXiv:2610.15093v1 Announce Type: cross Abstract: AI coding agents operate in iterative loops: they modify code, run tools, inspect the results, and decide what to do next. We call the design of this
arXiv:2610.14184v1 Announce Type: new Abstract: Studying model training requires checkpoint trajectories, whose storage cost limits temporal resolution. Although adjacent checkpoints are numerically c
arXiv:2610.14394v1 Announce Type: cross Abstract: Training large-scale recommender systems on dynamic industrial platforms, such as Short-Form Video (SFV) services with billions of daily interactions,
arXiv:2610.18291v1 Announce Type: new Abstract: Since the rise of supervised deep learning modelet dets, researchers has attempt to solve infrared small targection using various models like convention
[UPDATE / RETRACTION: The '100% GTO' claim had a prompt-leakage bug] We patched the repo to pass strictly neutral states, here are the real, honest numbers: • Latency: Still ~2ms (ONNX + Absorbing Mar
arXiv:2610.17383v1 Announce Type: new Abstract: Large-scale repositories of wearable sensor data have enabled the development of foundation models for human activities and behavior. However, existing
arXiv:2610.18858v1 Announce Type: new Abstract: Multimodal large language models have advanced rapidly, but most remain optimized for single-image inputs. Multi-image reasoning is costly because each
We just shipped web search in Private Mind, our open source app for running LLMs locally on iOS and Android. The video is the whole pitch: Qwen 3 1.7B with web off makes up Apple's September event, wi
arXiv:2610.17355v1 Announce Type: new Abstract: Video language models represent a video as a long sequence of visual embeddings in a decoder's input. Every visual embedding is processed by every decod
arXiv:2610.17434v1 Announce Type: new Abstract: Recent advances in video world models have enabled plausible interactive environments, yet long-horizon generation places a fundamental demand on visual
arXiv:2610.18846v1 Announce Type: new Abstract: Reconstructing complete, high-quality meshes of large-scale scenes from unposed multi-view images requires faithful geometric grounding while plausibly
You can't solve real-world physical tasks through autoregressive sampling alone. The physical world is entirely unforgiving to hallucination or approximate pattern matching. If we want actual autonomo
arXiv:2610.14802v1 Announce Type: new Abstract: End-to-end driving policies can achieve strong task performance while offering limited control over their driving style. Driving style describes how a v
tl;dr: running Qwen3.8FN Q4 locally is cheaper for me than every cloud model except Luna and the newer Haiku at mid-peak and peak electricity pricing where I live, and becomes the absolute cheapest mo
When we talk about agents, that doesn't necessarily mean we're talking about Python. In today's modern ecosystem, an agent might run as a high-concurrency Go microservice on Cloud Run, or live inside
arXiv:2610.13703v1 Announce Type: new Abstract: The fast pace in which protocols, frameworks, and technologies are being proposed for LLM-based agents results in a complex scenario for anyone aiming t
arXiv:2610.13744v1 Announce Type: new Abstract: On-policy self-distillation promises to replace the sparse outcome signal of verifiable-reward RL with dense token-level credit: a teacher conditioned o
arXiv:2610.13603v1 Announce Type: new Abstract: Psychology has proposed many principles of cognition. Each, however, was developed in isolation, leaving their combined explanatory power unknown. We as
arXiv:2603.03753v2 Announce Type: replace-cross Abstract: The ongoing shift of Artificial Intelligence (AI) from centralized cloud application programming interfaces (APIs) to local inference on edge
hexagon: add IM2COL_3D (#30305) hexagon: add IM2COL_3D support Assisted-by: OpenCode hexagon: add DMA paths for IM2COL_3D Assisted-by: OpenCode hexagon: avoid scalar fp16 conversions in IM2COL Assiste
arXiv:2505.22184v3 Announce Type: replace-cross Abstract: Social media platforms have experienced a significant rise in toxic content, including abusive language and discriminatory remarks, presenting
arXiv:2610.12703v1 Announce Type: cross Abstract: High-risk applications of deep learning require precise characterization of model decision-making. We conduct a systematic explainability evaluation a
- deepagents is durable by design - built on langgraph with state machine primitives hardener over years - deepagents is extendable, pick the exact pieces you want or make your own - deepagents is ope
arXiv:2610.13262v1 Announce Type: new Abstract: Memory-dependent manipulation requires a policy to track execution state and recover visual evidence that is no longer observable. We propose dual-strea
arXiv:2610.13025v1 Announce Type: new Abstract: Self-evolving agents are increasingly used to improve language model systems without human intervention through either weight updates or harness improve
arXiv:2610.12680v1 Announce Type: new Abstract: Background: Discontinuity in neonatal EEG is a critical marker of brain dysfunction but can be difficult to quantify visually. Inter-burst intervals (IB
arXiv:2610.12793v1 Announce Type: new Abstract: Pretrained vision-language-action (VLA) policies fail on memory tasks, behaviour that depends on events observed long before the current frame, because
arXiv:2610.12528v1 Announce Type: new Abstract: Continuous glucose monitoring (CGM) foundation models encode each day as one vector that mixes who the person is, what happened that day and how the sen
arXiv:2511.01047v4 Announce Type: replace-cross Abstract: Automated program repair (APR) has recently shifted toward large language models and agent-based systems, while prior work shows that reposito