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
New open source app built with Together AI! Gloss turns your saved articles, PDFs, and X bookmarks into a beautiful personal library, with lightning-fast AI answers powered by DeepSeek V4.1 Flash. Try
New open source demo app built by DeepSeek V4.1 Flash on Together AI! Try it → https://usegloss.io Introducing Gloss! A beautiful new way to save, read, and interact with articles. → Save articles, PD
arXiv:2610.14162v1 Announce Type: cross Abstract: Diffusion language models (DLMs) offer parallel sampling for faster generation than autoregressive models, an increasingly important advantage as infe
This model is a 74B parameter, 9B-active-parameter mixture-of-experts (MoE) model, packed into 24GB using 2-bit quantization with advanced quantization-aware training techniques to retain quality. It
arXiv:2610.18564v1 Announce Type: new Abstract: Aerial map matching provides position observations for navigation, but a position error alone does not determine how an observation should be weighted.
arXiv:2610.16895v1 Announce Type: cross Abstract: LLMs are used as high-level controllers for embodied agents, but it remains unclear whether they support collaborative reasoning, such as anticipating
London-based offensive security startup CodeWall Ltd. officially launched today with 4 million in new funding to give enterprises such as banks autonomous artificial intelligence agents that attack th
arXiv:2610.18829v1 Announce Type: new Abstract: With the rapid development of multimodal large language models (MLLMs), evaluating their video understanding capabilities has become increasingly import
arXiv:2510.17719v3 Announce Type: replace Abstract: Adherent raindrops on camera lenses are a pervasive source of real-world image degradation, undermining outdoor visual perception for downstream app
arXiv:2610.14344v1 Announce Type: new Abstract: Scaling deep learning models efficiently requires predictable performance transfer across compute regimes. Establishing reliable hyperparameter transfer
arXiv:2610.18727v1 Announce Type: new Abstract: Natural Language Autoencoders (NLAs) are proposed as oversight tools for language models: an Activation Verbaliser (AV) writes an English explanation of
arXiv:2610.17347v1 Announce Type: new Abstract: We revisit the statistical mechanics of Transformer attention via modern Hopfield models. We present a free-energy formalism to characterize parameter r
arXiv:2508.06163v2 Announce Type: replace-cross Abstract: Merging multiple task-specific fine-tuned checkpoints into a single multi-task model provides an attractive alternative to joint multi-task tr
arXiv:2610.14687v1 Announce Type: new Abstract: Many physical systems exhibit one-way coupling: exogenous fields such as medium density or obstacle geometry influence the dynamics without being affect
arXiv:2610.17203v1 Announce Type: new Abstract: Large language models can answer the same question in different styles, but users' preferred styles are hidden and vary across users and questions. We s
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:2610.17656v1 Announce Type: new Abstract: Reliable video reasoning requires models to produce correct answers and expose supporting visual evidence. Open-o3-Video enables verifiable reasoning by
OpenAI is in the news again. This time, it’s due to a recent incident involving corporate espionage. According to a statement the AI lab released on 13th October, the company discovered a “sophisticat
arXiv:2610.17143v1 Announce Type: new Abstract: Large language model (LLM)-based multi-agent systems are increasingly applied across diverse domains, yet different applications require different forms
arXiv:2610.18318v1 Announce Type: new Abstract: Over-parameterization is ubiquitous in modern machine learning, yet its effect on robustness remains poorly understood. We study this question in matrix
arXiv:2610.18404v1 Announce Type: cross Abstract: Automated radar waveform recognition classifies the waveform and modulation type of a received signal. As new waveform variants appear over time, a de
arXiv:2610.16308v1 Announce Type: new Abstract: Contact-rich insertion requires robots to combine visual alignment with tactile adjustment. However, existing visuotactile chunk-based policies collapse
arXiv:2610.18571v1 Announce Type: new Abstract: Different MRI modalities reveal different parts of a brain tumor. Segmentation models combine information from these modalities to outline tumor regions
arXiv:2610.15020v1 Announce Type: new Abstract: PATTERN, a synthetic node-classification benchmark still used to rank graph networks, plants a random subgraph in a random host graph and asks which nod
arXiv:2610.14586v1 Announce Type: new Abstract: This paper proposes a novel soft robot model named piece-wise constant 7D deformation (PC7) model that can represent expanding and contracting deformati
arXiv:2610.15456v1 Announce Type: cross Abstract: Accurate, physiologically consistent glucose forecasts could help people with type 1 diabetes respond to impending excursions. We applied our physiolo
arXiv:2610.15428v1 Announce Type: new Abstract: Context-based offline meta-reinforcement learning (COMRL) has advanced almost entirely through better task representations, which separate task identity
arXiv:2610.14558v1 Announce Type: new Abstract: Large pretrained models have achieved remarkable success across diverse domains, yet adapting them to multiple downstream tasks remains challenging: ful
arXiv:2606.12487v2 Announce Type: replace Abstract: Post-training quantization (PTQ) is essential for efficient large language model (LLM) inference, but reliably quantizing activations remains challe
arXiv:2610.17591v1 Announce Type: new Abstract: Estimating simulation-ready material parameters from visual observations is crucial for deformable-object manipulation but challenging because material
arXiv:2610.17260v1 Announce Type: new Abstract: To reconstruct a predictive 4D representation of the physical world from monocular video captured by a moving camera, we jointly reconstruct dynamic Gau
arXiv:2610.15947v1 Announce Type: cross Abstract: Heap-leaching hydraulics vary between regions of an ore bed, motivating fast prediction models that accommodate different material properties. This st
arXiv:2610.14844v1 Announce Type: cross Abstract: We introduce stochastic physics-informed neural networks (SPINNs) for stochastic boundary-value problems (SBVPs) with random operators. The method enf
arXiv:2610.18597v1 Announce Type: cross Abstract: Physical properties provide intuitive controls for sounds made by interacting objects. The challenge is to make a generative model respond predictably
arXiv:2610.15722v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) are good at video understanding and code generation, but it remains unclear whether they can recover the physic
arXiv:2610.16129v1 Announce Type: new Abstract: Deploying LLM agents in non-stationary environments requires continually revising their instructions as the task drifts, yet rewriting after every repor
arXiv:2610.18857v1 Announce Type: new Abstract: Pixel-space diffusion models provide an appealing alternative to latent-space diffusion models by directly modeling raw images without relying on a lear
arXiv:2610.18836v1 Announce Type: new Abstract: Vision-Language Models (VLMs) have achieved strong performance in visual perception and spatial reasoning, leading to growing interest in using them as
arXiv:2610.18865v1 Announce Type: new Abstract: Generating editable graphic designs requires arranging visual and textual elements into a coherent composition while preserving their content and editab
arXiv:2610.17991v1 Announce Type: new Abstract: Recovering high-quality images from degraded underwater observations is crucial for underwater exploration. Polarization observations show promise as an
arXiv:2610.14409v1 Announce Type: new Abstract: Generating an image with a diffusion or flow-matching model typically involves integrating a velocity field for hundreds of sequential steps. That compu
The generative AI functions in BigQuery (AI.GENERATE, AI.IF, AI.CLASSIFY, AI.SCORE, and more) bring large language models (LLMs) directly into your SQL, so a single query can classify millions of supp
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:2610.18054v1 Announce Type: cross Abstract: Anti-money laundering (AML) in financial networks requires modeling transaction patterns that span multiple institutions. In practice, however, banks
arXiv:2610.17016v1 Announce Type: new Abstract: Evaluating model uncertainty on real-world data is challenging because each instance provides only a single observed label, leaving true conditional cla
arXiv:2603.19844v3 Announce Type: replace Abstract: Multimodal MRI provides complementary information for brain tumor segmentation, but high accuracy alone does not reveal whether a model relies on cl
arXiv:2610.15614v1 Announce Type: new Abstract: Multi-label learning typically pursues model construction through the joint optimization of label fitting, correlation modeling, and structural regulari
arXiv:2610.18481v1 Announce Type: new Abstract: Protein sequence, structure, and functional annotations each capture complementary aspects of protein biology, yet existing tokenizers encode each modal
arXiv:2610.13989v1 Announce Type: cross Abstract: Evaluating recommender systems before deployment requires simulators that remain realistic over long, closed-loop interaction cycles. Current LLM-base
arXiv:2610.14635v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) have achieved remarkable progress across a wide range of multimodal tasks. However, object hallucination remains
arXiv:2511.18825v3 Announce Type: replace Abstract: Evaluating AI-generated video (AIGV) quality hinges on three crucial dimensions: visual quality, dynamic quality, and text-video alignment. While nu
arXiv:2603.13759v2 Announce Type: replace Abstract: Category-level multi-object trackers estimate trajectories for all detected instances, whereas some applications require propagating only targets sp
arXiv:2610.14519v1 Announce Type: new Abstract: Effectively eliciting the capabilities of large language models (LLMs) at inference time remains an important challenge. Existing studies address this c
MacStudio 128GB M1 ultra I'm curious how people who can run both models are deciding which one to work with. DeepSeekv4 benchmarks right below GPT 5.5 high. Flash Next benchmarks right above 5.4/5.5 x
Sampling: temp 1.0, top_p 0.95, top_k 20 for both. Run with evalscope over the OpenAI-compatible API: Qwen3.8-Next on Strata (MI50 32GB), Qwen3.8-27B on llama.cpp (RX 7900 XTX 24GB). Caveat: These are
arXiv:2610.18686v1 Announce Type: new Abstract: 3D semantic occupancy prediction is crucial for autonomous driving, but camera-based methods degrade in low-light conditions and LiDAR-based methods are
arXiv:2610.14039v1 Announce Type: cross Abstract: Existing vision-language-action (VLA) models benefit from large-scale vision-language pretraining, but tend to memorize training trajectories, limitin
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:2610.14326v1 Announce Type: new Abstract: Traffic density estimation from camera feeds requires connecting visual perception with short-horizon forecasting. We present a two-stage pipeline that