Knowledge catalogue
arXiv:2608.02650v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly rely on external tools to complete complex real-world tasks. However, reliable tool-use planning remains
arXiv:2608.02930v1 Announce Type: new Abstract: We revisit higher-arity atomic concept learning through the geometry of hypercubes and hyperplanes of ground instances. Our starting point is the observ
arXiv:2608.03917v1 Announce Type: new Abstract: Causal perception occurs when agents with competing Structural Causal Models (SCMs) of the same system infer different probability distributions, includ
arXiv:2608.03644v1 Announce Type: new Abstract: AI agents deployed in real-world settings must be capable of coordinating with humans and other AI agents they have not encountered before. Zero-shot co
arXiv:2608.02621v1 Announce Type: cross Abstract: Legal benchmarks typically score final answers even when models also state legal authority. We test whether answer correctness can serve as a proxy fo
arXiv:2608.03851v1 Announce Type: new Abstract: Real-time 3D perception is crucial for robotics, augmented reality, and embodied intelligence applications. Existing multi-view stereo (MVS) methods pri
arXiv:2608.03036v1 Announce Type: cross Abstract: Large Language Models (LLMs) are integrated into software systems and AI services, making efficient LLM serving a concern for software engineering. Se
arXiv:2608.03322v1 Announce Type: new Abstract: Medical visual grounding connects free-form clinical queries to spatial evidence in medical images and is an important component of interpretable medica
arXiv:2608.03803v1 Announce Type: new Abstract: Multilingual language models are deployed across a hundred or more languages, yet most benchmarks test whether a model can perform a task _in_ a languag
arXiv:2608.02642v1 Announce Type: cross Abstract: Accelerating scientific discovery is among the most consequential applications of AI, and computational biomolecular simulation stands out as a partic
arXiv:2608.02613v1 Announce Type: cross Abstract: Edge-deployed personal memory assistants must handle private interpersonal conversations on-device with open-weight models. Yet, existing memory bench
arXiv:2608.02892v1 Announce Type: new Abstract: Scene Graph Generation (SGG) is fundamental to structured visual understanding, yet existing benchmarks focus mainly on daily life images and overlook s
arXiv:2608.03275v1 Announce Type: new Abstract: Parameter-efficient fine-tuning (PEFT) enables efficient adaptation of large language models, but existing MoE-based PEFT methods typically improve capa
arXiv:2608.03428v1 Announce Type: cross Abstract: Image based dietary assessment offers a scalable alternative to self reported food diaries, yet fine-grained food recognition remains challenging due
Back in 2024 I tweeted screenshots of a game concept generated by GPT-3 and some concept 'art' created using DALL-E. Today, on the fourth anniversary of that tweet, I decided to see if Claude Fable 5
arXiv:2608.02942v1 Announce Type: new Abstract: Diffusion language models (dLLMs) can predict many tokens in parallel, but accurate generation still requires many iterative denoising steps. Few-step d
arXiv:2608.02691v1 Announce Type: cross Abstract: The key-value (KV) cache has become a major memory and bandwidth bottleneck in long-context large language model inference, making ultra-low-bit quant
arXiv:2608.03155v1 Announce Type: new Abstract: Autonomous exploration missions require decision-making under sensor uncertainty and computational constraints, yet integrating scientific representatio
arXiv:2608.03387v1 Announce Type: new Abstract: Humanoid robots have the potential to perform dexterous manipulation in human environments, yet acquiring diverse and generalizable skills remains costl
arXiv:2608.03631v1 Announce Type: new Abstract: Spatial relation questions require a model to identify the queried subject and object before comparing their layout. Yet a VLM can recognize both entiti
Some people are surprised that APIs (aka what Anthropic, OpenAI, and others provide) are treated differently than open weights in the new AI model framework. I'm not surprised at all, and it's actuall
arXiv:2608.03978v1 Announce Type: new Abstract: Stochastic single shooting trajectory optimization methods such as Model Predictive Path Integral control (MPPI) have been widely adopted in robotics du
arXiv:2502.08397v3 Announce Type: replace-cross Abstract: Clustering is a fundamental technique in data analysis and machine learning, used to group similar data points together. Among various cluster
arXiv:2603.01243v2 Announce Type: replace Abstract: Large language models (LLMs) are powerful tools that have found applications beyond human-machine interfaces and chatbots. Beside free-form generati
arXiv:2608.02985v1 Announce Type: cross Abstract: The standard check for contamination in LLM backtests is simple: compare scores before and after the training cutoff. We show this check is uninformat
arXiv:2608.03214v1 Announce Type: new Abstract: Large language models have transformed artificial intelligence from isolated prediction services into components of long-running, distributed systems th
arXiv:2508.12448v2 Announce Type: replace-cross Abstract: In-context learning (ICL) lets large language models (LLMs) solve new tasks from prompts alone, across an ever-widening range of domains, yet
Today, enterprise storage must be as agile, elastic, and responsive as the workloads it supports. Filestore, Google Cloud’s first-party, secure, scalable NFS file service, can service a wide-range of
arXiv:2608.03632v1 Announce Type: new Abstract: On-Policy distillation (OPD) transfers teacher capabilities by supervising student-sampled trajectories with dense token-level teacher signals. Recent s
arXiv:2608.01185v1 Announce Type: new Abstract: Recent 3D vision-language models (3D VLMs) construct geometry aware tokens by projecting 2D visual features into world coordinates, enabling spatial rea
arXiv:2608.00218v1 Announce Type: new Abstract: Agentic LLMs exhibit three consequential tool-use failures: invalid arguments (validity), unnecessary calls (over-calling), and omitted calls when tools
A pioneer of AI-in-biology just published a sharp rebuttal to the 'AI will cure cancer' narrative. The core argument: It's a measurement problem. Over 90% of drugs that enter clinical trials still fai
arXiv:2608.00434v1 Announce Type: new Abstract: Multi-Token Prediction (MTP) has emerged as an effective paradigm that augments a shared Large Language Model backbone with auxiliary heads, training th
arXiv:2608.00652v1 Announce Type: new Abstract: Human assistance in robotics spans around several tasks such as navigation, object manipulation, and placement, where a key challenge is selecting targe
arXiv:2608.00235v1 Announce Type: new Abstract: Vision-language models (VLMs) have emerged as a powerful framework for multimodal video understanding. However, they remain limited in the sign language
arXiv:2602.05220v4 Announce Type: replace Abstract: Current audio foundation models typically rely on rigid, task-specific supervision (e.g., speech recognition), addressing isolated factors of audio
arXiv:2608.00077v1 Announce Type: new Abstract: Visual-token pruning is usually judged by answer quality at a fixed retention budget. For text-rich multimodal large language models (MLLMs), this proto
arXiv:2608.01651v1 Announce Type: cross Abstract: Hybrid-attention large language models combine full attention with recurrent linear attention to reduce long-context inference costs, yet their autore
arXiv:2608.00678v1 Announce Type: new Abstract: Despite recent advances in Monocular Depth Estimation, state-of-the-art depth foundation models remain vulnerable to robustness issues. Particularly, ev
arXiv:2608.01021v1 Announce Type: cross Abstract: In an age of rapid model turnover, how do we make hallucination evaluation more perennial? We explore whether human-written hallucination samples coul
arXiv:2608.01172v1 Announce Type: new Abstract: We propose a workspace-fibered decomposition framework for motion planning in nR planar redundant manipulators operating in cluttered environments. Rath
arXiv:2608.01802v1 Announce Type: cross Abstract: Target-oriented vision-and-language navigation (VLN) on aerial platforms is attracting growing attention for missions such as disaster rescue, infrast
arXiv:2608.00674v1 Announce Type: new Abstract: Recent subject-to-image models have achieved impressive progress in personalized image generation, yet they still struggle to preserve fine-grained subj
arXiv:2608.01113v1 Announce Type: new Abstract: Text-driven instruction-based video editing in complex scenes remains challenging: purely textual prompts often fail to capture precise spatial relation
arXiv:2608.00261v1 Announce Type: new Abstract: Do frontier vision-language models present a coherent Theory-of-Mind (ToM) profile across tasks, matching the same human reference group, or does that p
I really like to use this one SQL benchmark when testing new models. I had another post some time ago with my benchmarks, but I decided to post a new one because of how well Deepseek did. I like the b
arXiv:2608.01263v1 Announce Type: new Abstract: On-policy distillation (OPD) samples trajectories from the current student policy and minimizes token-level divergence between student and teacher next-
arXiv:2603.00919v3 Announce Type: replace Abstract: Large language models (LLMs) have shown great promise for autonomous driving. However, discretizing numbers into tokens limits precise numerical rea
arXiv:2608.00994v1 Announce Type: cross Abstract: Zero-shot image captioning aims to generate image descriptions without annotated image-text pairs. Recent approaches exploit text-to-image models to s
arXiv:2608.00712v1 Announce Type: new Abstract: Multi hop question generation (MQG) aims to generate questions from multiple given documents and target answers, whereas question answering (QA) focuses
arXiv:2608.00024v1 Announce Type: new Abstract: Although diffusion models have revolutionized continuous domains like image synthesis through high quality generations and controllable guidance mechani
arXiv:2608.01104v1 Announce Type: new Abstract: Whole slide image (WSI) classification is an evidence-driven task, where diagnostic cues are often sparse, spatially organized, and class-dependent. Exi
arXiv:2608.02064v1 Announce Type: cross Abstract: Feed-forward networks (FFNs) account for a large fraction of Transformer parameters, yet their hidden width is usually constant across depth. We ask w
arXiv:2608.02353v1 Announce Type: new Abstract: Recent advances in agentic workflow optimization automate workflow design through task-specific workflow search or input-conditioned architecture select
arXiv:2509.22910v2 Announce Type: replace Abstract: Given that Visual SLAM relies on appearance cues for localization and scene understanding, texture-less or visually degraded environments (e.g., pla
arXiv:2608.01633v1 Announce Type: new Abstract: Large language models (LLMs) enable neural architecture search (NAS) directly over executable neural network programs. However, code-level flexibility d
arXiv:2506.03270v3 Announce Type: replace Abstract: While recent advances in vision-language models have accelerated language-guided robot planning, their black-box nature lacks the safety guarantees
arXiv:2603.15257v2 Announce Type: replace Abstract: Tactile sensing is a crucial capability for Vision-Language-Action (VLA) architectures, as it enables dexterous and safe manipulation in contact-ric
152 generations, deterministic grading (exact number/string/JSON/regex), no LLM judge on my 16GB laptop. task type | deepseek-r1:1.5b (1.1GB) | llama3.2:3b (2.0GB) | gemma:2b | codellama 7b arithmetic
arXiv:2608.01737v1 Announce Type: new Abstract: As digital drawings are increasingly shared online, reliable authorship verification has become important for protecting artists and resolving disputes.