Knowledge catalogue
arXiv:2610.01097v1 Announce Type: new Abstract: End-to-end research agents can now produce complete scientific papers, yet manuscript claims often diverge from executed experiments. This gap is struct
arXiv:2609.38864v1 Announce Type: new Abstract: Embodied tasks demand accurate, flexible, and semantically rich 3D scene representations. 3D semantic occupancy is well suited to this requirement, as i
arXiv:2609.39183v1 Announce Type: new Abstract: This paper studies extbf{thinking--answer consistency} in vision-language models. We focus on Visual Intention Grounding, where a model infers a target
arXiv:2609.38695v1 Announce Type: cross Abstract: Generative AI has dramatically accelerated the rate at which new treatments---from novel pharmaceuticals to online marketing campaigns---can be concei
arXiv:2609.38983v1 Announce Type: cross Abstract: Modern AI coding-agent harnesses (Claude Code, Codex CLI, Cursor) rest their security boundary on a largely unexamined assumption: that the action A a
arXiv:2609.39072v1 Announce Type: cross Abstract: Emotion recognition in conversation has been widely studied, but applying Large Language Models (LLMs) to continuous dimensional emotion evaluation in
arXiv:2609.39542v1 Announce Type: new Abstract: This report examines and compares some of the many fine tuning and prompting methods existing, applying them within the domain of autonomous driving. Th
arXiv:2609.38912v1 Announce Type: new Abstract: Agent harnesses govern how large language models (LLMs) gather context, invoke tools, verify results, preserve state, and terminate, largely affecting a
arXiv:2609.39263v1 Announce Type: new Abstract: A concept subspace's effect on model behavior does not establish how it relates to the output readout. We introduce a two-sided geometric diagnostic tha
arXiv:2609.40284v1 Announce Type: cross Abstract: Computer use agents (CUAs), which use graphical user interfaces (GUIs) to complete tasks on a computer, have recently surpassed human performance on m
arXiv:2609.39559v1 Announce Type: new Abstract: In this work we study the problem of MAPFC, a post-optimization step for Multi-Agent Path Finding (MAPF) plans where we are given a feasible plan produc
arXiv:2609.38536v1 Announce Type: cross Abstract: Diffusion-based large language models (dLLMs) promise to break the sequential latency bottleneck of autoregressive agents through parallel decoding, b
arXiv:2609.31688v2 Announce Type: replace Abstract: In verifiable domains such as math and coding, finding one correct solution among many attempts can matter more than the pass rate of each attempt.
arXiv:2609.39446v1 Announce Type: new Abstract: Existing full-duplex speech benchmarks cover only subsets of real-time interaction behaviors, often under limited contextual conditions. We introduce Du
arXiv:2609.39178v1 Announce Type: cross Abstract: Recently, Vision-Language-Action (VLA) models have revolutionized robotic manipulation by seamlessly integrating visual perception, language understan
arXiv:2609.35618v2 Announce Type: replace Abstract: The question of AI consciousness is one of the most urgent pre-emptive problems in philosophy and computer science, yet progress is hampered by a ca
Generative AI has made remarkable progress in creating increasingly realistic representations of the world. Image models can synthesize photorealistic scenes, video models can generate complex dynamic
arXiv:2609.38819v1 Announce Type: cross Abstract: Studying the alignment between the internal representations of vision models and the responses of the visual cortex to the same observed visual stimul
arXiv:2609.38285v1 Announce Type: cross Abstract: Vision-language models (VLMs) can contradict themselves across views of the same spatial relation and fail to respond when that relation changes. Addr
arXiv:2609.38524v1 Announce Type: cross Abstract: We consider estimating the one-step-ahead conditional distribution of a multivariate stochastic process. Many existing approaches rely on assumptions
arXiv:2609.39883v1 Announce Type: new Abstract: Video temporal grounding supports applications such as video search, content review, and automated editing by localizing events described in natural lan
arXiv:1806.11314v3 Announce Type: replace Abstract: Many works have been done on salient object detection using supervised or unsupervised approaches on colour images. Recently, a few studies demonstr
arXiv:2609.39380v1 Announce Type: new Abstract: Reliable infographic generation requires facts, symbols, and visual relations to remain consistent through rendering and revision. Correcting one elemen
arXiv:2510.13935v3 Announce Type: replace-cross Abstract: The facts a language model stores are tied to its parameter count, so small models that fit on edge devices fail on expert problems, which nee
arXiv:2609.38625v1 Announce Type: cross Abstract: Concept Bottleneck Models (CBMs) are designed to provide interpretable intermediate representations, yet how such bottlenecks affect robustness remain
A few days ago I released Jeff-Qwen3.5-0.8B, a small 'System 1' model that picks between options you define and returns a calibrated probability for each, in one forward pass. Speed was great on my M4
arXiv:2603.26741v2 Announce Type: replace-cross Abstract: Goal-conditioned visual navigation has been a long-standing testbed for embodied AI. We study a natural language-conditioned variant, language
arXiv:2609.39338v1 Announce Type: new Abstract: Knowledge distillation transfers knowledge by encouraging a student to match a teacher's predicted class probabilities. These probabilities express not
arXiv:2609.38743v1 Announce Type: new Abstract: LLM agents rely on retrieval tools to access external knowledge, yet visual agentic search remains severely bottlenecked by standard single-step retriev
arXiv:2410.02343v2 Announce Type: replace Abstract: Large language models (LLMs) routinely fail to output the correct option in multiple-choice question answering (MCQA) while encoding the answer inte
arXiv:2609.40305v1 Announce Type: new Abstract: Improving text-to-image models has traditionally relied on increasing model size or the number of denoising steps. In this work, we explore an alternati
arXiv:2609.39185v1 Announce Type: new Abstract: Mamba-style and hybrid language models compress their past into a fixed-size recurrent state that is rewritten at every generated token. Storing this st
arXiv:2609.39920v1 Announce Type: cross Abstract: Large vision-language models (LVLMs) exhibit strong multimodal in-context learning (ICL) capabilities, yet this ability degrades substantially as mode
arXiv:2507.09601v3 Announce Type: replace-cross Abstract: Financial text embeddings must distinguish changes in event status, perspective, and obligations even when passages share similar wording. NMI
arXiv:2609.38799v1 Announce Type: new Abstract: Understanding multi-perspective alternative narratives requires identifying how their information agrees, conflicts, or differs across sources. Existing
arXiv:2609.38766v1 Announce Type: new Abstract: Scientific agents can retrieve relevant passages yet still lose functional order, mix evidence across sources, or state conclusions that exceed the retr
arXiv:2609.38377v1 Announce Type: new Abstract: Evaluating the physical consistency of generated videos remains a fundamental challenge. Existing approaches rely on off-the-shelf vision-language model
arXiv:2609.40358v1 Announce Type: new Abstract: Video world models are expected to predict how the physical world evolves, yet they often produce visually plausible videos that violate basic physical
arXiv:2609.38593v1 Announce Type: cross Abstract: Skills are external artifacts that Large Language Models (LLMs) consume at inference time to improve their performance on specialized domains by incor
arXiv:2609.38526v1 Announce Type: cross Abstract: Scaling laws for optimization against reward models in AI alignment have pinned down how performance depends on optimization effort---measured by a KL
arXiv:2609.39581v1 Announce Type: cross Abstract: Paper ECG recognition is challenging because real-world ECG images vary in layout, physical artifacts, and label availability. We introduce RobECG-CL,
arXiv:2609.39788v1 Announce Type: new Abstract: Latent communication enables multi-agent systems to exchange information directly in internal representation space, reducing the token, computation, and
arXiv:2609.40316v1 Announce Type: cross Abstract: Looped transformers and Mixture-of-Experts (MoE) offer complementary routes to efficient scaling: recurrence increases computational depth at fixed pa
arXiv:2609.38309v1 Announce Type: cross Abstract: The search for physics Beyond the Standard Model (BSM) is generally limited not by the supply of theory descriptions but by the lack of discriminating
arXiv:2603.02561v2 Announce Type: replace-cross Abstract: Attention mechanism remains the defining operator in Transformers since it provides expressive global credit assignment, yet its quadratic cos
arXiv:2609.40245v1 Announce Type: cross Abstract: Robot navigation in dynamic, human-centered environments requires socially-compliant decisions grounded in robust scene understanding. Recent Vision-L
arXiv:2609.39048v1 Announce Type: cross Abstract: Protein optimization remains a longstanding goal in life sciences. Existing machine learning-assisted directed evolution (MLDE) methods primarily rely
Hello all, I wanted to share a little project I vibe-coded for myself that you may find useful. As many people here like to suggest, I wanted to give my small local LLMs access to information to impro
arXiv:2609.38792v1 Announce Type: new Abstract: We study training LLM judges from natural language feedback, especially for subjective tasks where the verdict depends strongly on which evaluation crit
arXiv:2609.39157v1 Announce Type: new Abstract: Video object removal presents a uniquely difficult editing challenge. Because a removal prompt specifies only what to erase rather than what to generate
arXiv:2609.39247v1 Announce Type: cross Abstract: Standard language model RL algorithms credit every token of a long rollout with the same advantage determined by the terminal reward. Actor-critic met
arXiv:2609.39086v1 Announce Type: cross Abstract: Runtime error healing lets a crashed program continue by generating code that repairs its live runtime state. Recent work shows that LLMs can generate
arXiv:2609.38641v1 Announce Type: new Abstract: Vision-Language-Action (VLA) foundation models have recently emerged as one of the prevailing solutions for autonomous driving, as they can utilize know
arXiv:2609.40031v1 Announce Type: cross Abstract: Digital image watermarking is increasingly critical in media contexts, as emerging regulations and industry practices require marking AI-generated con
arXiv:2609.38232v1 Announce Type: cross Abstract: Streaming spoken agents may take an external action before the available speech supports it, yet final-turn scores do not reveal whether each observed
arXiv:2609.38262v1 Announce Type: cross Abstract: Oversight changes the evidence it relies on. We ask when randomized audits and scoring align AI agents that can conceal misconduct and alter records.
40 year tech gap? No problem! The Tandy runs DeskMind, a native DOS program. It talks over WiFi (a PicoMEM 2 card with mTCP) to a small Python server on my PC. That server drives Qwen3.8-27B (NInfer o
arXiv:2609.25187v2 Announce Type: replace Abstract: Task planning bridges high-level instructions and executable behavior in long-horizon manipulation, yet modern Vision-Language-Action (VLA) systems
arXiv:2609.36058v1 Announce Type: new Abstract: Recent progress in reinforcement learning with verifiable rewards (RLVR) has highlighted the effectiveness of simple critic-free policy-gradient methods
arXiv:2607.11849v2 Announce Type: replace Abstract: Large language models (LLMs) have achieved remarkable performance on high-school and competition-level mathematics, yet their capabilities on advanc