Knowledge catalogue
arXiv:2606.02384v1 Announce Type: new Abstract: Progress in tabular machine learning has largely focused on increasingly sophisticated model architectures. At the same time, feature engineering remain
arXiv:2606.01020v1 Announce Type: new Abstract: Identifying logical fallacies in everyday discourse is challenging for many people. This challenge is amplified in the era of Large Language Models (LLM
arXiv:2606.01820v1 Announce Type: new Abstract: Fine-grained morphosyntactic error annotation is important in clinical and developmental language research, yet it is labour-intensive, expert-dependent
arXiv:2505.19489v2 Announce Type: replace Abstract: The Linux kernel is a critical system, serving as the foundation for numerous systems. Bugs in the Linux kernel can cause serious consequences, affe
arXiv:2606.00643v1 Announce Type: cross Abstract: Physics-Informed Neural Networks (PINNs) often train slowly or fail to converge on challenging partial differential equations (PDEs), a behavior recen
arXiv:2606.00662v1 Announce Type: new Abstract: This report presents TAP-JEPA, our runner-up submission to the EPIC-KITCHENS-100 (EK-100) Action Anticipation Challenge at EgoVis 2026. The task is to a
arXiv:2606.00487v1 Announce Type: new Abstract: Using a diffusion model for parallel drafting is a promising approach for speculative decoding. By predicting tokens at multiple future positions in a s
arXiv:2606.01421v1 Announce Type: new Abstract: We show that an array of scatterers which has been designed to have latent ('hidden') symmetries can be used as a sensor. We use the capacitance matrix
arXiv:2606.00880v1 Announce Type: cross Abstract: Continual reinforcement learning aims to produce agents that learn not only to improve at their current tasks but also to adapt as task distributions
arXiv:2606.01868v1 Announce Type: new Abstract: Reinforcement Learning (RL) has long served as a model for goal-directed animal behavior in neuroscience. Modern deep RL has shown remarkable success ac
arXiv:2606.00926v1 Announce Type: cross Abstract: Mechanistic studies of sequence models often treat layerwise state encodings as architectural traits: recurrent models concentrate readable state, att
arXiv:2606.00029v1 Announce Type: cross Abstract: Retrieval-augmented generation systems struggle with temporal reasoning and evidence fusion when answering complex questions over historical criminal
arXiv:2606.01213v1 Announce Type: cross Abstract: Despite tremendous recent progress, current text-guided image editing methods still struggle with many aspects of editing involving instruction follow
arXiv:2606.01613v1 Announce Type: cross Abstract: This paper presents an agentic retrieval-augmented generation (RAG) framework for domain-specific technical reasoning support, instantiated over a cur
arXiv:2602.06136v2 Announce Type: replace-cross Abstract: Test-time adaptation (TTA) offers a compelling remedy for machine learning (ML) models that degrade under domain shifts, improving generalisat
arXiv:2606.01106v1 Announce Type: new Abstract: TimeLogicQA evaluates whether video question answering systems can reason over temporal relations such as event existence, ordering, persistence, bounda
arXiv:2606.01176v1 Announce Type: new Abstract: Real temporal interaction streams carry predictive structure in short-horizon motif patterns -- repetition, reciprocity, star diversity, triadic flow --
arXiv:2606.01031v1 Announce Type: cross Abstract: Audio-driven talking-head generation has advanced rapidly, yet existing evaluation protocols mainly rely on frame-wise metrics that assume strict temp
arXiv:2605.24470v2 Announce Type: replace Abstract: Video-text retrieval has witnessed remarkable progress driven by large-scale vision-language pretraining, yet most existing approaches inherit an im
arXiv:2606.01520v1 Announce Type: new Abstract: A single action-conditioned latent predictive architecture can in principle be trained on the structured state of a driving scene, a robot workspace, or
arXiv:2606.01070v1 Announce Type: cross Abstract: Dense retrievers excel at first-stage candidate generation but lack effective reranking in zero-resource settings. Existing approaches face a fundamen
arXiv:2606.01112v1 Announce Type: new Abstract: Heterogeneous marine robotic systems composed of an unmanned surface vehicle (USV) and a hybrid remotely operated vehicle (HROV) have shown great potent
arXiv:2606.01050v1 Announce Type: new Abstract: Recent AI-generated image (AIGI) detectors perform well on natural-image benchmarks, but their behavior on text-rich forgeries, such as fabricated scree
arXiv:2602.02557v2 Announce Type: replace-cross Abstract: Recent advances in end-to-end trained omni-models have substantially improved audio capabilities by strengthening text-audio modality alignmen
arXiv:2606.00545v1 Announce Type: new Abstract: Post-trained language models can recognize their own outputs from a sentence or two out of context. In a companion paper itep{jack2026twomodes} we showe
arXiv:2606.01189v1 Announce Type: new Abstract: We argue that the AI community is now ready to move beyond benchmarking and consolidate scattered efforts in model analysis into a systematic discipline
arXiv:2606.00376v1 Announce Type: new Abstract: Extended chain-of-thought reasoning can degrade performance on deterministic state-tracking tasks, not due to preference biases, but limits rooted in th
arXiv:2602.09651v2 Announce Type: replace-cross Abstract: Diffusion models do not recover semantic structure uniformly over time. Instead, samples transition from semantic ambiguity to class commitmen
arXiv:2511.01938v3 Announce Type: replace-cross Abstract: Grokking is a puzzling phenomenon in neural networks where full generalization occurs only after a substantial delay following the complete me
arXiv:2606.02184v1 Announce Type: cross Abstract: These names do not exist. Elena Vasquez and Marcus Chen have appeared as volcano experts, astronauts, thriller protagonists, podcast hosts, and academ
arXiv:2606.00261v1 Announce Type: new Abstract: Police-reported crash statistics remain the standard input for urban road-safety assessment, but their incompleteness and reporting lag limit their usef
arXiv:2606.01901v1 Announce Type: cross Abstract: We introduce the Image Reconstruction Game, a fully automated benchmark in which a vision-language model issues corrective instructions to an image ge
arXiv:2606.00048v1 Announce Type: cross Abstract: Prior research has established that instruction-tuned large language models exhibit left-of-center political bias, measured exclusively through abstra
arXiv:2606.01847v1 Announce Type: cross Abstract: Diffusion-based Vision-Language-Action policies achieve remarkable success in robotic manipulation, yet commit a fundamental geometric error we term t
arXiv:2606.00182v1 Announce Type: cross Abstract: Human-AI collaboration is considered the most promising way to incorporate AI in the workplace. What remains unexplored are the experiential consequen
arXiv:2606.00674v1 Announce Type: cross Abstract: Large Language Models (LLMs) aligned via outcome-based Reinforcement Learning (RL) frequently exhibit a critical failure mode: they achieve high perfo
arXiv:2605.05427v2 Announce Type: replace Abstract: Refusal rates are a poor proxy for LLM safety, i.e., a model may over-refuse benign prompts while still complying with harmful ones. We audit both f
arXiv:2606.00291v1 Announce Type: cross Abstract: In RLHF, each training example contains a prompt x and two candidate responses y,y', and annotators provide pairwise preferences between these respons
arXiv:2606.00829v1 Announce Type: new Abstract: EgoCross evaluates multimodal large language models on egocentric video question answering under substantial domain shift, where test videos come from s
arXiv:2606.02093v1 Announce Type: cross Abstract: The task of Error Prediction, namely predicting whether a model output is correct, is commonly tackled with Uncertainty Quantification (UQ). However,
arXiv:2606.00344v1 Announce Type: new Abstract: Neural collapse is a structural property of the last-hidden-layer activations in neural network classification models, when trained beyond a zero classi
arXiv:2606.01202v1 Announce Type: new Abstract: Language models do not simply choose an answer at the output layer. In a 9,000-trajectory MMLU study across Qwen2.5-7B-Instruct, Llama-3.1-8B-Instruct,
arXiv:2510.10943v2 Announce Type: replace-cross Abstract: Bias in large language models (LLMs) remains a persistent challenge, often leading to stereotyping and unfair treatment across social groups.
arXiv:2606.01002v1 Announce Type: cross Abstract: Engression is a recently proposed and effective framework for conditional distribution learning. Its multi-step Reverse Markov extension further impro
arXiv:2606.01168v1 Announce Type: new Abstract: Chain-of-Thought (CoT) has significantly enhanced LLM reasoning, yet often incurs substantial computational overhead due to 'overthinking': generating e
arXiv:2606.02580v1 Announce Type: new Abstract: Inverse graphics is a longstanding and highly underconstrained problem that seeks to reconstruct images as editable 3D scenes which can be rendered, rel
arXiv:2606.01080v1 Announce Type: cross Abstract: Large language models often improve on difficult tasks by spending inference-time compute on a reasoning trace before producing the final answer. That
arXiv:2606.01738v1 Announce Type: cross Abstract: Multi-turn jailbreak attacks pose a growing threat to LLMs by exploiting conversational dynamics such as gradual escalation and cross-turn coordinatio
arXiv:2606.00966v1 Announce Type: new Abstract: Vision-Language Action (VLA) models continue to face challenges such as slow inference speed and difficulty performing fine-grained motion adjustments,
arXiv:2606.00516v1 Announce Type: new Abstract: Mixed batching (MB)--interleaving prefill and decode in a single batch--has become the standard scheduling strategy for large language model (LLM) infer
arXiv:2606.00592v1 Announce Type: new Abstract: Effective visual communication stems from the harmony of multiple design principles, such as readability, contrast, alignment, overlap, and coherence, w
arXiv:2606.02058v1 Announce Type: new Abstract: Event cameras emit asynchronous events in response to environmental appearance changes. The scarcity of real-world event datasets makes simulation essen
arXiv:2606.00232v1 Announce Type: new Abstract: We study fact-level repair for multimodal generation, where a fluent output may contain specific facts that are not supported by the input. Existing inf
arXiv:2606.01670v1 Announce Type: cross Abstract: Recently, Generative Recommenders (GRs) have emerged as a transformative recommendation paradigm by replacing traditional item IDs with semantic indic
arXiv:2606.01169v1 Announce Type: cross Abstract: Spacecraft collision avoidance for low-thrust satellites often requires determining not only how to maneuver, but also how late a maneuver can begin w
arXiv:2606.02142v1 Announce Type: new Abstract: The ongoing digitization has led to a proliferation of time-series data streams that monitor a variety of processes, from which valuable insights may be
arXiv:2606.01498v1 Announce Type: cross Abstract: Time series data inform critical decisions across many real-world domains. While large language model (LLM) agents can analyze data through natural la
arXiv:2606.00895v1 Announce Type: cross Abstract: This paper presents a fast, recursive neural solver for the J2-perturbed Lambert problem based on Tiny Recursive Models (TRM), termed the TRM-Perturbe
arXiv:2606.01591v1 Announce Type: new Abstract: The TimeLogic Challenge evaluates formal temporal-logic reasoning over video - 16 operators (before, after, until, since, always, co-occur, ordering, ..
arXiv:2606.01540v1 Announce Type: cross Abstract: Shapley values are a widely used tool for attributing importance and interactions among input variables in black-box models, but their computation inv