3,694 items tracked: 32 reported by two or more outlets, the rest by a single source. Most-corroborated first.
Partnered human-humanoid interaction couples locomotion with continuous physical contact.
Evaluation budgets in agentic retrieval-augmented generation span questions, search trajectories, and repeated answers.
Recent advances in 3D Gaussian Splatting (3DGS) have achieved remarkable performance in novel view synthesis, yet deploying both static and dynamic Gaussian representations on resource-constrained mobile devices remains…
Sparse-view novel view synthesis is a central problem in 3D content creation, but diffusion-based approaches remain limited by iterative denoising, making multi-view generation expensive at inference time.
Self-evolving reasoning models learn from their own generated questions, yet repeated self-training can lead to performance collapse.
Vision-language-action (VLA) models face a timing gap between low-rate inference and high-rate robot execution.
World-action models (WAMs) augment robot policies with action-conditioned environment dynamics, yet existing approaches largely rely on future observation reconstruction or generic latent prediction and lack structured,…
On-policy distillation (OPD) has emerged as a widely used paradigm for post-training large language models, reducing the train--test mismatch of conventional distillation by supervising the student on its own generated t…
Recently proposed Drifting Models shift iterative distribution refinement from inference to training, enabling effective one-step generation.
Reinforcement learning for long-horizon agents relies on purely retrospective training signals: credit is assigned only after observing environmental consequences, leaving the agent's belief at action time invisible to t…
Long-form thinking traces can substantially improve the multi-step reasoning performance of large language models (LLMs), but they introduce high inference-time overhead, with latency dominated by sequential decoding.
A benchmark score compares a system output against a reference, and methodological attention falls almost entirely on the first term.
We reconstruct high-fidelity 3D scene meshes from posed multi-view images without per-scene optimization, across scales ranging from single objects to large outdoor scenes.
Recent text-to-image generation models have achieved remarkable visual quality, but improving them through post-training remains challenging because no single reward signal captures the full range of human preference.
Recent text-to-image models have made substantial progress in photorealism, aesthetics, and text-image alignment.
We investigate a general-purpose layer for deep learning that, instead of compressing arbitrary-size training data into fixed-size weight matrices, stores a new pair of key-value representations for every data point duri…
Vision-Language-Action (VLA) foundation models have scaled rapidly to enhance manipulation performance and generalizability, but this scaling incurs high computational costs that render real-world deployment increasingly…
Language-model systems can separate contextual computation, persistent storage, and exact execution instead of updating all capabilities through one shared parameter system.
On-policy distillation (OPD) has become an important approach to language model post-training.
Cross-lingual contrastive learning has been a core component of multilingual encoder training, but the ability to explicitly align representations is not possible in decoder-only LLMs because of varying multilingual toke…
Many useful language-model tasks cannot be evaluated by exact outcome verification.
A trainable input embedding table assigns each vocabulary item an independently adjustable vector.
Language model agents are deployed with a harness, the software around the model that manages its context, tools, and feedback.
Biological reasoning models use post-training to connect LLMs to biological foundation model representations and biological text.
Multi-agent systems (MAS) built from large language models coordinate specialized agents to tackle complex tasks, but effective workflows are difficult to design in advance.
Recovering executable CAD programs from 3D meshes is challenging due to the compositional nature of CAD construction and the interaction between discrete modeling choices and continuous parameters.
Long-horizon compositional manipulation has become increasingly important for real-world robot deployment, where a single task involves multiple coordinated subtasks.
Vision-language-action models benefit from the understanding and reasoning capabilities of pretrained vision-language models, but action-only supervision provides limited grounding in world dynamics.
Existing synthetic image evaluators typically provide only a scalar quality score and do not identify the image regions that support it.
In this paper, we study how to achieve one-step action generation in Robotic Foundation Models (RFMs), aiming to overcome the high inference latency of multi-step flow matching.
Distribution Matching Distillation (DMD) trains a few-step student from the difference between separately estimated target and student scores, so it must keep an auxiliary diffusion model fitted to the student's evolving…
Enterprises adopting retrieval-augmented generation (RAG) face a recurring operational decision: promote, revise, or block a system version.
Extreme space-weather events can damage power systems on Earth and degrade GPS accuracy and satellite operations.
Rubric-based reinforcement learning (Rubric-RL) trains language models where no verifier exists.
Diffusion models with prompt and reference image-guided editing have seen rapid progress, yet they remain too coarse for pixel-level control.
Large Language Models (LLMs) have been used for novel discovery of algorithms, theorems, drugs, and other tasks through the use of harnesses that prompt an LLM to iteratively optimize an objective.
Autoregressive (AR) grounding models serialize spatial predictions, introducing sequential latency and imposing a causal order on output tokens.
Precise grounding matters.
Given a target dataset, such as faces with eyeglasses, and a background dataset, such as faces without, contrastive analysis separates salient factors specific to the target from common content shared by both.
Multi-Head Latent Attention (MLA) enables expressive multi-head attention with compact caches for its content and decoupled RoPE paths, yet cache memory still scales linearly with context length and batch size.
Foundation models can serve as clinical agents through tool-use harnesses.
Recent joint video-audio generation models have achieved strong semantic correspondence and temporal synchronization.
Long-context LLM agents accumulate interaction histories that strain KV-cache memory and attention computation.
Text-to-image diffusion models are personalized to a subject by DreamBooth fine-tuning on a handful of its images.
Reinforcement learning with verifiable rewards (RLVR) has improved the reasoning capabilities of large language models (LLMs), yet their predictions remain sensitive to task-irrelevant prompt features.
Iterative self-distillation enables LLM agents to learn from successive deployments, offering a path toward recursive self-improvement (RSI).
Modern transformers pair impressive capabilities with substantial memory and compute demands.
Repeated training on model-generated data can degrade later models.