Knowledge catalogue
arXiv:2609.22091v1 Announce Type: new Abstract: Retrieval over a personal memory store is retrospective: it surfaces what resembles the query, and it is blind to what the user has committed to do. We
arXiv:2609.24995v1 Announce Type: new Abstract: Understanding natural human instructions is crucial for deploying robots in human-centric environments. We study multimodal instruction grounding, where
arXiv:2609.24145v1 Announce Type: new Abstract: We present MimicAgent, a prompt-to-trajectory generation framework for learning dynamic quadruped skills. Although reward shaping is extensively used wh
Some people here say MiMo-V2.6 is bad with tools and are going back to GLM-5.3-Flash. I spent today running MiMo-V2.6-Flash-RL as the backend for an agent harness, on 2× DGX Spark with vLLM, using the
MiMo-V2.6 is 'simply' the best (for now). Despite its simple architecture design it's currently No.1 in the open-weight benchmarks (weighted average). With 'simple,' I mean a classic Grouped Query Att
arXiv:2609.23336v1 Announce Type: new Abstract: Localizing and describing fine-grained differences between near-identical images is a critical yet underexplored capability for multimodal large languag
arXiv:2609.23679v1 Announce Type: new Abstract: Form Field Detection (FFD) is a fundamental component of document understanding systems, enabling applications ranging from large-scale industrial digit
Saw this today and found it very intriguing. Lots of interesting design choices here, and it's cool to see someone doing something different. Here's a few highlights: Looped transformer: dynamic recur
arXiv:2609.22954v1 Announce Type: new Abstract: Mobile gas-sensing inspection requires a mobile platform to reliably reach ordered sampling poses. We present MIRA-PRM, a mission-informed probabilistic
arXiv:2609.22778v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) are increasingly used as evaluators, yet their reliability in professional assessment tasks that require expert
arXiv:2609.23999v1 Announce Type: new Abstract: How large language models (LLMs) integrate patient risk with clinical cost tradeoffs remains poorly understood. We investigated how four open-weight LLM
arXiv:2505.12254v3 Announce Type: replace Abstract: Existing visual place recognition (VPR) datasets predominantly rely on vehicle-mounted imagery, offer limited multimodal diversity, and underreprese
arXiv:2609.23980v1 Announce Type: cross Abstract: AI agents now report vulnerabilities faster than maintainers can review them. Reports often depend on security properties specific to the application,
Recently, the new DeepSeek-V4.1-Flash architecture showed how a causal encoder-decoder can work, but it was trained from scratch. Model Grafting does it to an existing model: cut at some depth, let th
arXiv:2603.15265v2 Announce Type: replace Abstract: Developing a unified policy for multi-task robotic manipulation remains challenging due to policy degradation from task interference and negative tr
arXiv:2609.23073v1 Announce Type: new Abstract: Recent advances in natural language processing have led to molecular Large Language Models (LLMs) with strong performance across diverse chemistry tasks
arXiv:2609.24071v1 Announce Type: new Abstract: Chart reasoning agents are increasingly used to extract actionable insights in critical domains, achieving state-of-the-art performance on multiple benc
arXiv:2609.22643v1 Announce Type: new Abstract: Forecasting a long horizon from only the first observations of a sequence is ill-posed: many trajectories are consistent with the same short history. We
arXiv:2609.22272v1 Announce Type: new Abstract: We formulate Artistic Intelligence as exploration driven world realization, leaving space for creative possibility while preserving the semantic, artist
arXiv:2609.24812v1 Announce Type: new Abstract: Voice provides a natural and immediate interface for AI agents. Many settings in which voice agents could be useful, including meetings, households, and
arXiv:2609.23416v1 Announce Type: cross Abstract: Long-form audio performance is often summarized by context length and aggregate accuracy, obscuring how language, evidence, and task jointly shape dif
arXiv:2609.22690v1 Announce Type: new Abstract: We develop an index policy for finite-horizon Bernoulli multi-armed bandits from minimax solutions to single-arm bandit (SAB) problems. Each SAB problem
arXiv:2609.22398v1 Announce Type: cross Abstract: Accurate delineation of bi-atrial structures from late gadolinium enhancement MRI (LGE-MRI) is an important prerequisite for structural analysis and f
arXiv:2609.24678v1 Announce Type: cross Abstract: Continual learning with Low-Rank Adapters (LoRA) typically mitigates forgetting by penalizing the overlap between a new update and the accumulated pas
Must-read papers of the week ▪️ JEPA-Anything ▪️ Modality-Autoregressive World-Action Models ▪️ In-Context Robot Learning with VLM Agents ▪️ Dream-RSI: Recursive Self-Improvement through Evolving Worl
arXiv:2602.09765v2 Announce Type: replace Abstract: Previous Vision-Language-Action models face critical limitations in navigation: scarce, diverse data from labor-intensive collection and static repr
arXiv:2609.24391v1 Announce Type: new Abstract: Voice-controlled interaction in industrial settings is hampered by acoustic noise, which severely degrades audio-only speech recognition. Audio-visual s
arXiv:2509.00754v3 Announce Type: replace Abstract: Dempster--Shafer theory (DST) provides an attractive framework for multi-source information fusion. However, its effectiveness critically depends on
arXiv:2609.23087v1 Announce Type: new Abstract: Modern Transformer design and compression both reduce to allocating capacity under a budget. The standard scalars for these decisions, #Params and #FLOP
New on Dedicated Model Inference: canary rollouts. Upgrade the model behind a live endpoint without downtime. Traffic moves from your current deployment to the new checkpoint in gated steps (default 5
This post is written by a human and I'd appreciate it if you treated it as such. Thanks. So, I've been noticing a pretty clear interest in developing as good a coding and agentic tool-calling model as
To build and deploy sophisticated robotics applications that can perceive, reason and act in dynamic environments, developers need new physical AI models and tools. The ROS open framework is a project
arXiv:2609.23417v1 Announce Type: cross Abstract: Screen-recorded web editing requests contain weak deictic expressions such as ``this'' and ``there,'' whose referents depend on speech, cursor traject
arXiv:2609.23088v1 Announce Type: new Abstract: Educational foundation models must solve problems, understand curriculum structure, diagnose learner difficulties, and provide appropriate instructional
arXiv:2609.22215v1 Announce Type: new Abstract: Knowledge distillation can transmit unintended behavioral traits from a teacher model to a student through training data that appear semantically unrela
arXiv:2609.24377v1 Announce Type: cross Abstract: We study latent-space watermarking through a pretrained generator using a prescribed latent-to-output stochastic mapping, called the renderer. A water
arXiv:2609.24983v1 Announce Type: new Abstract: We present onPanda, an interactive tool for efficiently annotating LLM alignment data and agent trajectories. onPanda adopts token-level correction as i
Ming-Image-0.1-Design creates complete UIs, dashboards, infographics, and posters from structured prompts of up to 8K tokens, with consistent layouts, typography, colors, and imagery. It can also nati
David Gewirtz / ZDNET: OpenAI launches GPT-6 Sol and Luna, saying Sol makes about half as many mistakes as GPT-5.6 Sol and Luna matches GPT-5.6 Sol's performance at ~1% of the cost — GPT-6 Sol and Lun
arXiv:2609.24202v1 Announce Type: new Abstract: Sparse attention reduces the quadratic cost of global self-attention while retaining strong empirical performance, but how its restricted interactions s
arXiv:2609.23055v1 Announce Type: new Abstract: Discrete diffusion models now match autoregressive language models on several benchmarks, while the question of how best to train them has received far
Opus 5.5 is the best frontier model for parsing tables in PDFs. We ran it through ParseBench, and it scored 93.9%, a 7%+ increase over Opus 5, and beating Fable/Gemini/Astra. It's comparable to LlamaP
On 22 September 2026, Allie K. Miller posted on Twitter that the Opus 5.5 model led her to curse at Claude less frequently. She notes that while reducing profanity toward another AI is an undesirable
arXiv:2609.22285v1 Announce Type: new Abstract: Adapting language models to new domains via continual pre-training raises a basic evaluation problem: if the training corpus overlaps with what the mode
arXiv:2609.24128v1 Announce Type: cross Abstract: Judge-specific sensitivity is useful for aggregating pairwise LLM evaluations, but its interpretation depends on which systematic presentation effects
arXiv:2609.24890v1 Announce Type: new Abstract: Evaluation of Computer-Use Agents (CUAs) is often limited to the final deliverables they create (at the end of hundreds of steps) and assessed with func
Over the last few hours, some requests to the deepseek-v4.1-flash model on Ollama were charged at an incorrect rate, leading to higher usage consumption than expected for certain users. Sorry about th
arXiv:2609.23784v1 Announce Type: new Abstract: Robotic bin packing requires long-horizon sequential decision-making, as each object placement affects the available space for subsequent packing. Exist
arXiv:2609.22157v1 Announce Type: cross Abstract: KV-cache eviction methods decide which tokens to keep but not whether to evict at all, so a benchmark mean can hide a class of inputs on which compres
arXiv:2609.22771v1 Announce Type: cross Abstract: Recent advances in Audio LLMs have achieved human-level speech recognition, yet existing systems struggle to capture paralinguistic aspects such as sp
People got upset at me for saying this, but there are no companies outside the US and China even *trying* to build frontier AI (perhaps Korea and UK are close), despite marketing claims. Governments s
arXiv:2609.22281v1 Announce Type: new Abstract: Foundation models have recently demonstrated strong capabilities across a wide range of medical imaging tasks. However, their performance in structured
arXiv:2609.23463v1 Announce Type: new Abstract: Federated learning lets multiple parties train a shared model without pooling their data, but a client with far less data than the others can end up poo
arXiv:2609.23600v1 Announce Type: new Abstract: Prompt learning efficiently adapts vision-language models (VLMs) to downstream tasks, but gains on seen classes often come at the expense of generalizat
arXiv:2609.24133v1 Announce Type: new Abstract: Recent advances in humanoid robotics and embodied intelligence have enabled robots to perform increasingly complex manipulation tasks. However, musical
arXiv:2609.22200v1 Announce Type: new Abstract: LLM assistants and agentic systems log long multi-turn conversations. AI providers often scan these conversations for Personally Identifiable Informatio
arXiv:2609.23554v1 Announce Type: new Abstract: Low-cost planar air-bearing testbeds have matured into a standard proxy for free-flying spacecraft GNC, but they remain largely thruster-only and are ra
arXiv:2609.22789v1 Announce Type: new Abstract: Image-to-layer decomposition converts a flattened image into editable RGBA layers, enabling element-level editing in design workflows. Existing diffusio
arXiv:2609.22868v1 Announce Type: new Abstract: End-to-end driving requires planning-relevant bird's-eye-view (BEV) representations, but existing pretraining approaches often rely on task annotations
arXiv:2609.22916v1 Announce Type: new Abstract: Generating text-rich images from prompts requires both textual fidelity and the coherent integration of text into the surrounding image. An explicit lay