Knowledge catalogue
arXiv:2608.30315v1 Announce Type: cross Abstract: Token embeddings are the basic representational units that connect discrete tokens with continuous computation in language models. Although modern lan
arXiv:2608.29613v1 Announce Type: new Abstract: Function vectors (FVs) have recently emerged as a promising mechanism for steering the behavior of large language models (LLMs) by injecting task-specif
arXiv:2608.28696v1 Announce Type: new Abstract: Visual in-context learning (ICL) with multimodal large language models (MLLMs) is effective for fine-grained visual classification, but each retrieved i
arXiv:2608.29286v1 Announce Type: new Abstract: As Multimodal Large Language Models (MLLMs) evolve into sophisticated interactive assistants, their reliability depends not only on following instructio
arXiv:2608.31017v1 Announce Type: cross Abstract: Ambient AI scribes draft clinical notes under the reassurance that a clinician signs every note. We audited three commercial AI scribes on the same 14
arXiv:2608.29905v1 Announce Type: new Abstract: Text-guided style editing of 3D assets is essential for adapting existing objects to diverse visual aesthetics in digital content creation. Despite rapi
arXiv:2608.29270v1 Announce Type: cross Abstract: Autoformalization translates informal mathematical theorems into code for proof assistants such as Lean. A central challenge is that current evaluatio
arXiv:2606.21803v2 Announce Type: replace Abstract: Next-token prediction is the self-supervised signal that trains language models, and every observed prompt token provides the same signal at test ti
arXiv:2608.29923v1 Announce Type: new Abstract: Open-vocabulary semantic segmentation (OVSS) relies on vision-language alignment to recognize arbitrary text-defined categories, yet this alignment is f
arXiv:2608.30720v1 Announce Type: new Abstract: Representational similarity is foundational to analyses of deep networks, yet distances between point-valued representations are not intrinsically tied
arXiv:2608.31059v1 Announce Type: cross Abstract: When do text embeddings work as inputs to empirical analysis? Their use rests on an assumption: that we can trade text for its low-dimensional embeddi
arXiv:2608.26164v1 Announce Type: new Abstract: Large language models can interpret natural-language chemistry questions, but their internal reasoning is difficult to inspect, constrain, and validate.
arXiv:2608.27115v1 Announce Type: new Abstract: Cross-lingual alignment in multilingual language models is typically attributed to joint training: shared parameters, mixed-language batches, or explici
arXiv:2608.27072v1 Announce Type: cross Abstract: A core question in decision-making for agents is whether the relative priorities of competing lower-level objectives can be determined by emotional pr
arXiv:2608.26743v1 Announce Type: new Abstract: Enterprises fine-tune language models on proprietary data that may later require removal due to privacy, contractual, or compliance obligations. Selecti
arXiv:2608.26720v1 Announce Type: new Abstract: Robotic and edge intelligence systems operate in dynamic environments where data arrives continuously, requiring models to adapt while preserving previo
arXiv:2608.26160v1 Announce Type: new Abstract: Nowadays semantic models provide limited support for representing distributed AI workflows and their execution across heterogeneous edge, fog, and cloud
arXiv:2608.26872v1 Announce Type: new Abstract: On-policy distillation (OPD), which leverages a pre-trained, specialized teacher model to provide dense supervisory signals, has achieved significant su
arXiv:2411.15129v3 Announce Type: replace-cross Abstract: What can we learn about language from studying how it is used by ChatGPT and other large language model (LLM)-based chatbots? In this paper, w
arXiv:2608.26125v1 Announce Type: cross Abstract: Online hate against Muslim communities often appears in culturally coded, multilingual forms that evade conventional AI moderation. Such systems, thou
arXiv:2608.27190v1 Announce Type: new Abstract: Accurate 3D segmentation of cone-beam CT (CBCT) is critical for interventional and radiation therapy applications, yet it remains limited by two compoun
arXiv:2608.24958v1 Announce Type: cross Abstract: An audio language model is a black box in a specific way: we see what it says, never what it works out on the way there, and chain-of-thought monitori
arXiv:2511.11635v2 Announce Type: replace-cross Abstract: In intelligent education, personalized mathematics question generation aims to produce mathematics questions that satisfy educational requirem
arXiv:2505.22084v2 Announce Type: replace Abstract: Characterizing and quantifying gender representation disparities in audiovisual storytelling contents is necessary to grasp how stereotypes may perp
arXiv:2412.12660v2 Announce Type: replace Abstract: Recently, developing unified medical image segmentation models gains increasing attention, especially with the advent of the Segment Anything Model
arXiv:2511.00260v2 Announce Type: replace Abstract: Anatomy-aware colonoscopic navigation requires localizing partial endoscopic observations on a stable 3D reference to support coverage assessment, r
arXiv:2608.23593v1 Announce Type: cross Abstract: Text-to-image systems use learned aesthetic scorers to filter training data and guide generation, but whether these scores encode demographic attribut
arXiv:2410.18321v3 Announce Type: replace-cross Abstract: Confidence calibration matters wherever a classifier's probabilities, not just its labels, are consumed downstream. We study Focal Calibration
arXiv:2608.24524v1 Announce Type: cross Abstract: Feature attribution is a central tool of model interpretability, yet the software through which it is applied remains fragmented: individual tools spe
arXiv:2608.24273v1 Announce Type: new Abstract: Continual knowledge graph embedding updates entity and relation representations as a graph grows. Existing methods primarily address catastrophic forget
arXiv:2608.23794v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) scales language models by routing each input through a small set of independently parameterized experts. We show that copying
arXiv:2608.24662v1 Announce Type: new Abstract: Large language models (LLMs) are commonly evaluated under the assumption that their observable behavior is primarily determined by model weights, traini
arXiv:2608.23978v1 Announce Type: new Abstract: Visual grounding is typically evaluated as a one-shot mapping from an informative referring expression to a visual target. This formulation misses a cen
arXiv:2608.21450v1 Announce Type: new Abstract: Knowledge-Based Visual Question Answering (KB-VQA) relies on retrieving external information to answer queries involving long-tail entities. However, ex
arXiv:2608.21486v1 Announce Type: new Abstract: Deep face recognition (FR) models reach near-saturated accuracy but remain opaque: a practitioner cannot ask which semantic attributes a similarity scor
arXiv:2608.22974v1 Announce Type: new Abstract: Large language model (LLM) agents rely heavily on knowledge encoded in model parameters or presented as unstructured context. In domain-specific tasks,
arXiv:2608.21332v1 Announce Type: new Abstract: Deep-learning models of anatomy can be numerically plausible yet anatomically impossible, and they generalize poorly when data are scarce. We introduce
arXiv:2608.20637v1 Announce Type: cross Abstract: Static analyzers have been widely adopted for vulnerability detection in C/C++ programs. Query-based static analyzers (e.g., CodeQL) encode vulnerable
arXiv:2506.13583v2 Announce Type: replace-cross Abstract: Reinforcement Learning (RL) agents often exhibit learning behaviors that are not intuitively interpretable by human observers, which can resul
arXiv:2606.15867v2 Announce Type: replace Abstract: Multi-subject reference-based image generation requires jointly preserving multiple human identities, binding per-person objects and fashion items,
arXiv:2601.21948v2 Announce Type: replace Abstract: Neural visual decoding is a central problem in brain-computer interface research, aiming to reconstruct human visual perception and to elucidate the
arXiv:2608.20384v1 Announce Type: new Abstract: Multimodal affect and behaviour classifiers that fuse heterogeneous text, audio, and visual streams must simultaneously achieve competitive accuracy and
arXiv:2608.21247v1 Announce Type: new Abstract: Token compression has become a key technique for reducing the inference cost of large foundation models, with approaches such as token pruning and KV-ca
People have been talking to each other for at least 100,000 years, as best we can tell. And in all that time, there has been only one thing in the world that could learn a human language to perfect fl
arXiv:2510.13922v2 Announce Type: replace-cross Abstract: Clinical notes contain unstructured text provided by clinicians during patient encounters. These notes are usually accompanied by a sequence o
arXiv:2608.21133v1 Announce Type: new Abstract: Medical image-text data can expose protected health information (PHI) through both visible image content as well as accompanying text, creating a barrie
arXiv:2608.20640v1 Announce Type: cross Abstract: Multi-merchant e-commerce catalogs contain equivalent and related products under different merchant-scoped identifiers, fragmenting behavioral evidenc
arXiv:2608.21236v1 Announce Type: new Abstract: Representation engineering offers a lightweight means of controlling language-model behavior by modifying intermediate hidden states, but its direct app
arXiv:2608.20685v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) has no model of time: when a fact changes across a coding session - a function is renamed, an endpoint moves, a d
arXiv:2608.20480v1 Announce Type: new Abstract: Optimal learners are tailored to exploit the i.i.d. data assumption underlying the classic PAC model. What if an i.i.d. training sample were corrupted w
Scientific terms should have precision. If we use the terms VLM, VLA, WAM in an indiscriminate fashion, as is becoming common in robotics, we are not helping clarity in communication. Let's keep the h
arXiv:2608.19888v1 Announce Type: cross Abstract: Streaming systems that maintain a pool of expert models must repeatedly decide whether to reuse an existing expert for arriving data, spawn a new one,
arXiv:2608.19215v1 Announce Type: new Abstract: Given deep uncertainty about the possibility of artificial consciousness, it is unclear how we should treat potentially sentient AI. On the one hand, we
arXiv:2608.19472v1 Announce Type: new Abstract: Lexical semantic change (LSC) is commonly modelled through vector-space representations, but these approaches often provide limited insight into which a
arXiv:2608.19825v1 Announce Type: cross Abstract: Medical image captioning is a technique that accelerates early-stage diagnostic workflows and enhances the interpretability of medical diagnostic AI s
arXiv:2608.20054v1 Announce Type: new Abstract: Multi-module systems often expose every module to the full input. We test whether restricting evidence visibility changes which solutions gradient-based
arXiv:2608.18710v1 Announce Type: new Abstract: Recent advances in generative video models have enabled camera-controlled world video generation, allowing models to synthesize videos under user-define
arXiv:2608.18654v1 Announce Type: new Abstract: Medical image captioning requires translating heterogeneous visual evidence into concise clinical descriptions, where errors in findings, assertion stat
arXiv:2608.19009v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly paired with verifiers (step checkers, self-consistency filters, tool-based fact checkers, formal proof ass
arXiv:2608.18438v1 Announce Type: cross Abstract: Modern mental healthcare faces a critical shortage of senior supervisory oversight, leading to a 'supervision gap' where novice therapists manage high