Knowledge catalogue
arXiv:2602.04692v3 Announce Type: replace Abstract: Referring Multi-Object Tracking (RMOT) aims to track specific targets based on language descriptions, playing a vital role in interactive AI systems
arXiv:2610.14945v1 Announce Type: new Abstract: Visual localization enables unmanned aerial vehicles (UAVs) to maintain absolute positioning in GNSS-denied environments. A common approach matches UAV
arXiv:2610.14106v1 Announce Type: new Abstract: Large language models can translate natural-language instructions into plausible manipulation plans, but robotic execution requires physically grounded
arXiv:2610.16268v1 Announce Type: new Abstract: Test-time-training (TTT) layers update fast-weight memory while processing an input sequence. A gradient-based update, however, does not by itself estab
arXiv:2610.15166v1 Announce Type: new Abstract: Coding agents are increasingly evolving beyond reproducing what a world looks like toward constructing executable worlds that capture how a world works.
arXiv:2610.16329v1 Announce Type: new Abstract: Accurate breast cancer risk prediction from screening mammography is essential for improved risk stratification and personalized screening. It can benef
arXiv:2610.15595v1 Announce Type: new Abstract: In real-world indoor fire environments, visual degradation severely impairs instruction grounding, waypoint prediction, and long-horizon exploration in
arXiv:2610.17630v1 Announce Type: cross Abstract: In outdoor environments, varying terrain and contact conditions can cause identical action commands to produce different motion outcomes for quadruped
arXiv:2610.15707v1 Announce Type: new Abstract: A central desideratum in model editing is generalization to complex tasks, which prior work formalizes under a direct generalization paradigm: treating
arXiv:2601.07632v5 Announce Type: replace Abstract: Discrete motion tokenization has recently enabled Large Language Models (LLMs) to serve as versatile backbones for motion understanding and motion-l
arXiv:2610.14852v1 Announce Type: new Abstract: Reinforcement learning (RL) is promising for spatial text-to-image generation, but existing work largely focuses on policy optimization, assuming accura
arXiv:2603.29602v2 Announce Type: replace-cross Abstract: Existing multi-turn image editing paradigms are often confined to isolated single-step execution. Due to a lack of context-awareness and close
arXiv:2610.16502v1 Announce Type: new Abstract: Discovering and disambiguating entities from multimodal and heterogeneous data is a key challenge in discovery science, where relevant knowledge is ofte
arXiv:2610.16634v1 Announce Type: cross Abstract: Recent Vision-Language-Action (VLA) models increasingly use natural-language instructions to condition autonomous driving behavior. Yet existing close
Went down the rabbit hole to map the different Post-Transformer architectures. Various directions include Dragon Hatchling (BDH), Mamba, RWKV, xLSTM, Titans, and a bunch of hybrid models coming from d
arXiv:2610.18535v1 Announce Type: new Abstract: Video understanding benchmarks are the primary yardstick for measuring progress in video-language modeling, and a growing body of work relies on them to
arXiv:2610.17792v1 Announce Type: new Abstract: GUI grounding enables web agents to translate natural-language instructions into actionable interface locations. However, dense layouts and small, visua
arXiv:2610.18642v1 Announce Type: new Abstract: The Key-Value (KV) cache constitutes a dominant source of memory consumption during large language model (LLM) inference, particularly in long-context a
arXiv:2502.13034v4 Announce Type: replace-cross Abstract: In recent years, a substantial body of work in visually grounded natural language processing has focused on real-life multimodal scenarios suc
arXiv:2610.18176v1 Announce Type: cross Abstract: Proactive human-robot collaboration requires autonomous systems to infer not only immediate actions but also the underlying hierarchical intentions go
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:2610.14022v1 Announce Type: new Abstract: On-policy distillation (OPD) improves language-model by supervising a student on prefixes sampled from its own policy, but its supervision remains confi
arXiv:2610.15224v1 Announce Type: cross Abstract: Natural language specifications let non-expert users task robot teams, and large language models (LLMs) have recently proven effective at grounding su
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:2610.13991v1 Announce Type: new Abstract: Self-evolving agents improve through repeated cycles of modification and evaluation. However, existing methods receive feedback on modifications only af
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:2610.14770v1 Announce Type: new Abstract: Multimodal contrastive learning typically relies on manually specified scoring functions, such as cosine similarity, to quantify the similarity between
arXiv:2610.15669v1 Announce Type: new Abstract: Weak bag-level labels are widely available in computational pathology, whereas reliable instance-level annotations for whole-slide images remain expensi
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: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:2610.17426v1 Announce Type: new Abstract: Clinical decision-making is a sequential process of information collection, clinical inference, and forecasting under partial observability, often witho
arXiv:2610.15814v1 Announce Type: new Abstract: General-purpose multimodal foundation models are increasingly capable of directly controlling robots, yet improving their manipulation capabilities thro
arXiv:2610.18295v1 Announce Type: new Abstract: Detectors of logical anomalies, such as missing, extra or wrongly combined parts, usually score a test image by its distance from normal (good) images.
arXiv:2610.14030v1 Announce Type: new Abstract: Looped transformers reuse one shared block across many recurrent steps, so depth becomes a quantity that can be spent at runtime rather than a stack of
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:2610.15467v1 Announce Type: new Abstract: Image-computable low-level image saliency has shaped perceptual psychology and computer science, but is limited by its inability to capture human high-l
arXiv:2610.15124v1 Announce Type: new Abstract: Foundation models need to support diverse inference budgets, yet training a separate model for each budget duplicates pretraining effort. Elastic models
arXiv:2610.14671v1 Announce Type: new Abstract: Streaming video understanding requires answering questions from the observed video, with evidence drawn from recent observations or earlier events. Hist
arXiv:2610.14512v1 Announce Type: new Abstract: Objective. To evaluate whether spatial context and temporal modeling improve tissue recognition during optical trocar entry, where multiple abdominal-wa
arXiv:2601.17673v2 Announce Type: replace Abstract: Unified remote sensing multimodal models exhibit a pronounced spatial reversal curse: Although they can accurately recognize and describe object loc
arXiv:2610.18697v1 Announce Type: cross Abstract: World models (WMs) and world-action models (WAMs) focus on future world prediction and executable action generation, respectively. Although these mode
arXiv:2610.16735v1 Announce Type: new Abstract: Multimodal reinforcement learning with verifiable rewards commonly assigns one sequence advantage to an entire response. This outcome-level signal disti
arXiv:2610.15915v1 Announce Type: new Abstract: Reusable skills improve multimodal agents without updating model weights, but their effectiveness depends on both the evidence presented and the procedu
arXiv:2610.16441v1 Announce Type: new Abstract: Current image-text evaluation often relies on a global score, which gives limited insight into which semantic details are supported by the image. Explai
arXiv:2610.15092v1 Announce Type: new Abstract: Quantization plays a crucial role in efficiently deploying deep learning models on resource-constrained devices. Post-training quantization does not req
arXiv:2610.17242v1 Announce Type: new Abstract: Can a vision-language model tell left from right? Modern VLMs solve visual puzzles and follow hour-long videos, yet when asked whether the camera moved
arXiv:2610.15929v1 Announce Type: new Abstract: Recent trackers built on foundation models such as the Segment Anything Model (SAM) achieve strong performance by propagating object masks through memor
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
David Silver is one of the all-time greats. He was the creator of AlphaGo, which changed the course of history by showing that neural nets could achieve superhuman performance for the first time. He a
Every few weeks, a new model steps up and claims best-in-class at something. The launch chart makes the case, the link makes the rounds, and your team is back to the question nobody has time for: shou
Last week we announced that Gemini Enterprise has evolved to make it even simpler to get work done, and introduced the Gemini agent, your new universal agent for work. It's always on and ready to answ
Many months in the making, MNX is finally live! Whether the AI bubble bursts or not, AI is changing our lives forever. I'm in awe of how this technology has reached something close to escape velocity.
IBM Research has presented a new approach that scales AI‑driven chip design by employing open “agent factories,” lowering inference cost by 11.5 × compared to fully proprietary setups. The method enab
Suggestion for you: Pick an agent for work, and pick an agent for personal. You could explore to do this all with Grok Bot (with many different types of bots) Personally, I like @bot for work, and @Mu
I am an independent researcher. Due to budget constraints, I shifted my 21B MoE pre-training—which I had originally planned to run on 64 H100s—to a single NVIDIA GH200 ($2.29 per hour), and I have com
arXiv:2610.12571v1 Announce Type: new Abstract: Most systems trained by equilibrium propagation or coupled learning are in the same class as multi-layer perceptrons: while they may be universal functi
arXiv:2610.13821v1 Announce Type: new Abstract: A useful language model should know when to answer and when to say 'I don't know.' Can we improve that decision by training the model itself or by train
arXiv:2610.13057v1 Announce Type: cross Abstract: Counterfactual text editing is the ability to revise a given text in light of a hypothetical change while preserving facts not causally affected by th
arXiv:2610.12837v1 Announce Type: cross Abstract: Knowledge distillation aims to train a smaller student model to mimic a larger teacher model for resource-constrained environments. However, the proce