Knowledge catalogue
arXiv:2609.34838v1 Announce Type: new Abstract: On-policy distillation (OPD) trains student agents through teacher supervision on their own interactions with an environment. However, in asynchronous m
arXiv:2609.33083v1 Announce Type: new Abstract: Sparse video understanding often requires selecting a small set of visual evidence under a fixed frame budget. Most sparse selectors allocate this budge
arXiv:2609.34742v1 Announce Type: new Abstract: Recent studies suggest that large language models encode emotion concepts as structured internal representations, but most existing work focuses on text
arXiv:2602.00449v2 Announce Type: replace-cross Abstract: Latent Chain-of-Thought aims to enable step-by-step computation without emitting long rationales, yet its internal mechanisms remain unclear.
arXiv:2609.35039v1 Announce Type: new Abstract: Vision-Language-Action (VLA) policies trained with behavior cloning or flow matching are optimized to output an action trajectory, but they cannot expre
arXiv:2609.35364v1 Announce Type: new Abstract: Many temporal link predictors summarize past interactions through learned node representations. We examine whether simple counts of recurring interactio
arXiv:2609.33791v1 Announce Type: new Abstract: Since the advent of knowledge distillation, KL divergence has been the standard loss in distillation. Recently, on-policy distillation (OPD) has emerged
arXiv:2609.34058v1 Announce Type: new Abstract: AI systems often feel brittle and fragmented. A large language model (LLM) may correctly explain a concept but fail to apply it, or follow safety instru
arXiv:2609.33707v1 Announce Type: cross Abstract: Vision-language-action (VLA) models adapt pretrained vision-language models (VLMs) for closed-loop robot control, transferring their perceptual and se
arXiv:2609.33536v1 Announce Type: new Abstract: Large language model (LLM) serving is increasingly constrained by the GPU memory consumed by key-value (KV) caches. Existing compression, eviction, and
arXiv:2609.31680v1 Announce Type: new Abstract: Joint-embedding predictive architectures (JEPA) have emerged as a promising self-supervised pretraining paradigm for time series, learning representatio
arXiv:2609.34621v1 Announce Type: new Abstract: Native 3D texture generation synthesizes colors directly in 3D space for a given geometry, conditioned on multi-view reference images. It is generally b
arXiv:2609.32525v1 Announce Type: new Abstract: The widely used Transolver family of neural operators is based on physics-attention, which softly assigns the points of an unstructured mesh to a small
arXiv:2609.31985v1 Announce Type: new Abstract: Vision-language pretraining objectives differ in the spatial granularity of their supervision, yet the implications of this distribution for chest X-ray
arXiv:2609.31882v1 Announce Type: new Abstract: Reward-based diffusion fine-tuning faces practical challenges when desirable outcomes are rare or conditioning corrections are costly to estimate. In th
arXiv:2609.33490v1 Announce Type: cross Abstract: Conditional independence (CI) is a fundamental concept in statistics and machine learning. Recent advances in conditional generative modeling provide
arXiv:2609.35289v1 Announce Type: new Abstract: Denoising Diffusion Probabilistic Models have shown remarkable performance in unconditional image generation. In order to generate images with desired s
arXiv:2609.33279v1 Announce Type: new Abstract: Irregularly sampled multivariate time series (ISMTS) are prevalent in real-world applications, where both observation times and available measurements c
arXiv:2609.34933v1 Announce Type: new Abstract: Memorization has been proposed as a mechanism to explain how language models fit the tail of their training distributions, but its training dynamics are
arXiv:2602.22107v2 Announce Type: replace Abstract: Checkpoint selection is a standard component of neural network training, yet the validation criterion used to select a checkpoint is often chosen he
arXiv:2609.34911v1 Announce Type: cross Abstract: Modern robot policies predict a chunk of future actions from a single observation, execute only a prefix, and discard the rest before replanning. Choo
arXiv:2609.33828v1 Announce Type: new Abstract: Optimization layers enable the incorporation of structured constraints and decision problems into learning systems. Training such systems requires diffe
arXiv:2609.34325v1 Announce Type: new Abstract: Vision Transformers (ViTs) incur quadratic self-attention cost in the number of tokens. Most token-reduction methods adapt token identities within a pre
arXiv:2609.31970v1 Announce Type: new Abstract: Women's presence in Congress has stalled below 30%. That institutional underrepresentation is mirrored by their limited visibility on televised news, wh
arXiv:2609.33166v1 Announce Type: new Abstract: In-context reinforcement learning (ICRL) enables large language model agents to adapt to new environments using their interaction history without updati
arXiv:2609.32215v1 Announce Type: new Abstract: Transformers have redefined sequential recommendation by effectively modeling dynamic user behaviors and long-range dependencies. However, they remain i
arXiv:2609.32705v1 Announce Type: new Abstract: While content-adaptive schemes have delivered notable advances in image super-resolution (SR), existing approaches typically focus on texture complexity
arXiv:2602.08847v2 Announce Type: replace Abstract: Multi-agent LLM systems enable advanced reasoning and tool use via role specialization, yet reliable reinforcement learning (RL) post-training for s
arXiv:2609.35634v1 Announce Type: new Abstract: Electrocardiogram (ECG) recordings are corrupted by non-stationary noise sources that degrade diagnostic reliability, particularly in ambulatory and lon
arXiv:2609.32628v1 Announce Type: new Abstract: Video generation has broad applications in content creation and entertainment. Diffusion transformers have advanced the quality of generated videos, but
arXiv:2609.32453v1 Announce Type: new Abstract: Robotic manipulation is inherently history-dependent, yet most pretrained robotic policies condition on only the current observation or a short temporal
arXiv:2609.35242v1 Announce Type: new Abstract: Scalable Vector Graphics (SVG) are essential for modern industrial Computer-Aided Design (CAD). However, existing autoregressive SVG generation models a
arXiv:2609.34253v1 Announce Type: new Abstract: Pretrained autoregressive Transformers represent a large sunk investment in compute. Existing conversion methods reuse that investment by changing eithe
arXiv:2606.18307v2 Announce Type: replace Abstract: Data selection for instruction tuning is usually studied for efficiency, reaching strong performance with a fraction of the training data. We ask wh
arXiv:2609.35106v1 Announce Type: new Abstract: Predicting cellular responses to perturbations is a central problem in cellular biology, with broad applications in systems biology and drug discovery.
arXiv:2609.33148v1 Announce Type: new Abstract: World-action models give visual navigation agents a way to anticipate how candidate actions will change future observations and to act from the predicte
arXiv:2609.34921v1 Announce Type: new Abstract: Predicting Drug-Target Interactions~(DTIs) is a central task in computational drug discovery, with direct applications in virtual screening, drug repurp
arXiv:2609.32253v1 Announce Type: new Abstract: Vision-language-action (VLA) models have achieved strong performance in language-conditioned manipulation, yet success under nominal evaluation does not
arXiv:2609.33711v1 Announce Type: new Abstract: On-policy distillation (OPD) trains a student on its own responses with token-level feedback from a stronger teacher, yet the teacher can fail on questi
arXiv:2509.22828v2 Announce Type: replace Abstract: Rearranging objects in cluttered tabletop environments remains a long-standing challenge in robotics. Classical planners often generate inefficient,
arXiv:2512.09814v2 Announce Type: replace Abstract: Personalized Text-to-Image (PT2I) generation aims to produce customized images based on reference images. A prominent interest pertains to the integ
arXiv:2609.33693v1 Announce Type: new Abstract: Learning PDE operators on complex domains requires capturing interactions among fields on vertices, edges, and faces, alongside global responses shaped
arXiv:2609.33172v1 Announce Type: cross Abstract: World-Action models (WAMs) trained on static demonstrations often fail to manipulate moving targets even when they possess the required manipulation s
arXiv:2603.12099v2 Announce Type: replace Abstract: The da Vinci Research Kit (dVRK) has been widely used for research in robot-assisted surgery over the past decade, and its latest generation, the dV
arXiv:2609.32957v1 Announce Type: new Abstract: Diagnosing a patient from video requires more than recognizing the sign: a vision-language model must turn what it sees into hypotheses, questions and t
arXiv:2609.35704v1 Announce Type: new Abstract: Video generation must account for two sources of motion, one induced by the observer's camera path and the other caused by scene dynamics. An ideal came
arXiv:2609.33980v1 Announce Type: new Abstract: Dynamic graph anomaly detection requires repeated decisions as graph structure and class prevalence drift, yet detector benchmarks usually score a fixed
arXiv:2609.33530v1 Announce Type: cross Abstract: Natural Language Understanding (NLU) plays a crucial role in various applications, yet its performance suffers from weaknesses in handling the complex
arXiv:2609.34346v1 Announce Type: new Abstract: Temporally dense optical flow is essential for dynamic perception in immersive VR/AR systems, where rapid head, hand, and object motion must be continuo
arXiv:2609.35099v1 Announce Type: new Abstract: We present e3j, a fast Euclid-equivariance backend for geometric deep learning applications with JAX bindings for GPU and TPU. Leveraging both optimized
arXiv:2412.16633v4 Announce Type: replace Abstract: LLM-based robots use Large Language Models (LLMs) as planners to translate natural language instructions into policies such as grasp(), move_to(), a
arXiv:2609.33117v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) can now interpret a standard ten-second, twelve-lead electrocardiogram (ECG) with clinically grounded, reward-v
arXiv:2609.34893v1 Announce Type: new Abstract: Learning-based manipulation policies relying on RGB cameras often suffer from degraded observations under extreme exposure. Event cameras mitigate this
arXiv:2609.34729v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) are effective for learning node and link embeddings through permutation-equivariant aggregation. However, standard GNNs col
arXiv:2507.21616v3 Announce Type: replace Abstract: We study the output representation of a neural network used for next event prediction. We propose partitioning the time axis into a fixed set of int
arXiv:2609.35167v1 Announce Type: new Abstract: Machine learning (ML) increasingly powers Internet of Things (IoT) applications at the edge. Yet producing a deployable edge ML artifact for a specific
arXiv:2609.35570v1 Announce Type: cross Abstract: Vision-language navigation (VLN) models perform well but target compute-rich platforms, limiting deployment on memory- and power-constrained robotic e
arXiv:2609.32360v1 Announce Type: new Abstract: Geospatial simulation of infrastructure interventions requires mobility generators that respond directly to edited maps, yet many data-driven generators
arXiv:2609.32930v1 Announce Type: cross Abstract: Brain-computer interfaces (BCIs) have emerged as transformative technologies that enable direct communication between the brain and external devices.
arXiv:2609.33962v1 Announce Type: cross Abstract: Subject-independent motor-imagery (MI) EEG decoding can exhibit subject-level failures even when average performance appears acceptable: under subject