Knowledge catalogue
arXiv:2610.15514v1 Announce Type: new Abstract: Structured pruning reduces the inference cost of large language models (LLMs) by permanently removing neurons and weight rows, yielding dense, hardware-
arXiv:2610.14911v1 Announce Type: cross Abstract: Multi-human cooperative object manipulation is a highly challenging topic in humanoid control. While existing methods can handle simple collaborative
arXiv:2610.14833v1 Announce Type: new Abstract: Robust manipulation under uncertain object dynamics and geometry remains a core challenge in real-world robotics. Policies trained under fixed assumptio
arXiv:2610.15734v1 Announce Type: new Abstract: We present ScenePlacer, a framework for scene-level pose estimation of objects generated by state-of-the-art native shape generation models, placing gen
arXiv:2605.05965v2 Announce Type: replace Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has become a key approach for improving the reasoning abilities of large language models. Howe
arXiv:2610.15258v1 Announce Type: cross Abstract: We introduce Sequent-Prover, a family of verifier-using language-model agents, and the post-training framework that produces them. Agents reason in an
arXiv:2610.16457v1 Announce Type: new Abstract: Humans expand their locomotion capability by wearing appropriate footwear, such as hiking boots for mountains or skates for ice. Footwear changes the gr
arXiv:2610.16106v1 Announce Type: new Abstract: Multimodal entity alignment (MMEA) is fundamental to integrating heterogeneous knowledge graphs (KGs), yet existing paradigms remain critically vulnerab
arXiv:2512.10581v2 Announce Type: replace Abstract: Current methods for all-in-one image restoration increasingly rely on complex mechanisms, such as Mixture-of-Experts or prompt learning, to handle d
arXiv:2610.18807v1 Announce Type: new Abstract: Agentic reinforcement learning (RL) enables large language models (LLMs) to learn from multi-turn interactions with verifiable outcomes. Textual skills
arXiv:2610.15764v1 Announce Type: new Abstract: Audio-Visual Segmentation (AVS) requires predicting pixel-wise masks of sounding objects by grounding acoustic signals in visual space. In multi-source
arXiv:2610.15953v1 Announce Type: cross Abstract: Small area estimation (SAE) traditionally borrows strength across domains through a prespecified working model. We introduce small area learning (SAL)
arXiv:2610.17427v1 Announce Type: new Abstract: Trajectory smoothness has been proposed as a cheap, training-free signal for curating imitation-learning demonstrations, most recently by rinse, which i
arXiv:2610.16946v1 Announce Type: new Abstract: Descriptions of how people use AI are becoming training data for the next generation of models. We ask whether what a model reads about its users change
arXiv:2610.17808v1 Announce Type: new Abstract: Pixel-level annotation for chest X-ray (CXR) lesion segmentation is expensive, making active learning (AL) essential. However, existing AL strategies fa
arXiv:2610.14400v1 Announce Type: new Abstract: Successor-feature-based zero-shot reinforcement learning methods pre-train a task encoder and successor-feature predictor on offline, reward-free data,
arXiv:2610.13996v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards improves mathematical reasoning when a final answer can be checked, but a correct answer does not certify
arXiv:2610.14405v1 Announce Type: cross Abstract: Reinforcement learning (RL) has driven substantial progress in coding agents by relying on verified successful trajectories as learning signals. Howev
arXiv:2606.19774v2 Announce Type: replace Abstract: Action chunking enables robot policies to produce temporally coherent behavior, but generating multi-step action sequences with flow-based policies
arXiv:2610.17925v1 Announce Type: new Abstract: Decisions that weigh several reward signals against each other require the joint distribution of the return vector. Categorical critics scale exponentia
arXiv:2610.14567v1 Announce Type: cross Abstract: This paper develops strong Gaussian approximations (KMT type) for constant learning rate stochastic gradient descent (SGD). We work with heavy tailed
arXiv:2610.15512v1 Announce Type: new Abstract: Coherent multi-shot audio-visual video generation requires maintaining consistent identities while depicting evolving states and coordinating sounds acr
arXiv:2503.07775v3 Announce Type: replace Abstract: Resource-efficiently computing representations of probability distributions and the distances between them while only having access to the samples i
arXiv:2610.15322v1 Announce Type: cross Abstract: Enabling the reuse and composition of knowledge and capabilities distributed across foundation models is an important step toward building scalable ar
arXiv:2603.06280v2 Announce Type: replace Abstract: Long-horizon mobile manipulation needs whole-body demonstrations, and collecting them is the bottleneck. Keeping the robot in the loop ties the data
arXiv:2610.18110v1 Announce Type: cross Abstract: Multimodal medical data captures complementary aspects of disease. It provides a comprehensive basis for diagnosis and the identification of biologica
arXiv:2610.14440v1 Announce Type: new Abstract: Asynchronous reinforcement-learning post-training of large language models is computationally efficient but inherently off-policy: the learner updates o
arXiv:2610.18256v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) has emerged as a popular training paradigm for LLMs, providing dense, token-level supervision by aligning a model's o
arXiv:2610.18459v1 Announce Type: new Abstract: External tools can extend the capabilities of small language models (SLMs), enabling their deployment in resource constrained environments. However, the
arXiv:2610.15589v1 Announce Type: new Abstract: Many deployed distillation pipelines show the student a truncated view of the teacher: keep the top-k probabilities, renormalize, and minimize a diverge
arXiv:2610.17746v1 Announce Type: new Abstract: A robot may know how to perform a task yet fail when a human asks for it naturally. We study this human--VLA communication gap by separating an informat
arXiv:2511.08328v2 Announce Type: replace Abstract: Regular mammography screening is crucial for early breast cancer detection. By leveraging deep learning-based risk models, screening intervals can b
arXiv:2610.18447v1 Announce Type: cross Abstract: World models have emerged as a promising paradigm for embodied AI, yet existing systems often remain fragmented in the modalities they model and the f
arXiv:2610.16383v1 Announce Type: new Abstract: Elite athletics throwing provides a structured biomechanical action sequence together with an objective continuous outcome, namely throw distance, makin
arXiv:2610.16448v1 Announce Type: new Abstract: Diffusion models, particularly Diffusion Transformers, achieve strong image and video generation quality but remain expensive at inference time due to r
arXiv:2610.16794v1 Announce Type: new Abstract: Proximal Policy Optimization (PPO) is widely used in reinforcement learning with verifiable rewards for language-model reasoning. While value evolution
arXiv:2610.17999v1 Announce Type: new Abstract: Humanoid behavior foundation models (BFMs) enable diverse whole-body control, but adapting a pretrained controller to a new embodiment remains challengi
arXiv:2610.15038v1 Announce Type: new Abstract: Real-world Vision-Language Navigation (VLN) requires agents to act under partial observability, where map structure, semantic cues, and target locations
arXiv:2610.17593v1 Announce Type: cross Abstract: Language provides a natural interface for humans to specify and reason about goals, but training language-conditioned robotic policies and reasoning t
arXiv:2610.14683v1 Announce Type: new Abstract: Large language model (LLM)-based AI Scientists advance scientific discovery, yet they suffer from inefficiencies due to noisy observations. Existing pri
arXiv:2610.15164v1 Announce Type: new Abstract: This paper studies the backbone used by metrics for evaluating the quality of generated images. Although generative models have advanced rapidly, some o
arXiv:2610.16517v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models are often pretrained via imitation learning, making reinforcement learning (RL) post-training important when deplo
arXiv:2602.02331v2 Announce Type: replace Abstract: Achieving highly dynamic parkour with humanoid robots on complex terrains unseen during the pre-training stage remains a challenge in robotics. Alth
arXiv:2610.14077v1 Announce Type: cross Abstract: Embodied Audio-Visual Navigation (AVN) requires an agent to locate sound targets by jointly leveraging visual and auditory cues. While prior work has
arXiv:2512.00724v3 Announce Type: replace Abstract: Reward models (RMs) are critical to reinforcement learning from human feedback (RLHF). However, policy models can exploit biases or spurious correla
arXiv:2610.17996v1 Announce Type: new Abstract: Sugarcane leaf diseases severely impact crop yield and quality, making accurate and timely detection critical for sustainable agriculture. Conventional
arXiv:2610.16070v1 Announce Type: cross Abstract: Frontier models are now trained for complex multi-agent tasks, from running a company to engaging in negotiations. These tasks necessitate training mo
arXiv:2606.13209v2 Announce Type: replace Abstract: Reward models (RMs) are a key component of reinforcement learning from human feedback, enabling the alignment of large language models with human va
arXiv:2601.17673v2 Announce Type: replace Abstract: Unified remote sensing multimodal models exhibit a pronounced spatial reversal curse: Although they can accurately recognize and describe object loc
arXiv:2610.16945v1 Announce Type: new Abstract: Recent advances in multimodal foundation models, exemplified by GPT-6 Astra, raise the prospect of general-purpose embodied reasoning and planning. Usin
arXiv:2610.18356v1 Announce Type: new Abstract: City-scale 3D grounding is commonly formulated as candidate ranking, which requires precomputed instance proposals and becomes inefficient in large outd
arXiv:2610.18189v1 Announce Type: new Abstract: Modern text-to-video (T2V) models generate visually compelling videos, yet meaning-preserving changes in prompt wording can substantially alter semantic
arXiv:2610.14260v1 Announce Type: new Abstract: Augmentation-based self-supervised learning can recover the content shared across views without separating its underlying factors into individual coordi
arXiv:2610.15888v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards spends much of its rollout budget on states that yield no learning signal. We recast this as a question a
arXiv:2610.16735v1 Announce Type: new Abstract: Multimodal reinforcement learning with verifiable rewards commonly assigns one sequence advantage to an entire response. This outcome-level signal disti
arXiv:2610.14634v1 Announce Type: new Abstract: Continuous indoor-outdoor navigation connects destination-level reasoning with motion decisions that must respond to current observations. We present Vb
arXiv:2610.14885v1 Announce Type: new Abstract: Test-time compute (TTC), which scores multiple candidate actions at inference time, is a powerful way to improve the execution performance of vision-lan
arXiv:2602.16681v2 Announce Type: replace Abstract: Time-series anomaly detection (TSAD) requires identifying both immediate Point Anomalies and long-range Context Anomalies. However, existing foundat
arXiv:2610.14000v1 Announce Type: new Abstract: Group-relative reinforcement learning methods such as GRPO train large language model (LLM) agents by comparing rollouts for the same task. When every t
arXiv:2610.16860v1 Announce Type: new Abstract: How the relationship between image-text aligned and vision-only models changes across development remains unknown. We applied time-resolved representati