3,694 items tracked: 32 reported by two or more outlets, the rest by a single source. Most-corroborated first.
arXiv:2606.25001v2 Announce Type: replace-cross Abstract: Machine unlearning (MU) is commonly judged by output forgetting, such as low forget-set accuracy or reduced membership inference.
arXiv:2606.31653v2 Announce Type: replace-cross Abstract: Certified training aims to produce models whose predictions can be formally verified against adversarial perturbations, typically by optimising upper bounds on th…
arXiv:2607.16004v2 Announce Type: replace-cross Abstract: Increases in photovoltaic generation, charging of electric vehicles and heat-pump demand challenge operating limits in low-voltage distribution grids.
arXiv:2607.22766v2 Announce Type: replace-cross Abstract: Post-training alignment of Large Language Models is increasingly bottlenecked by data quality: preference and instruction-tuning corpora accumulate label noise, s…
arXiv:2608.06202v2 Announce Type: replace-cross Abstract: Large language model (LLM) benchmark evaluations are routinely used to support claims about model safety, reliability, and deployment readiness.
arXiv:2608.30386v2 Announce Type: replace-cross Abstract: Hybrid linear-attention architectures have recently scaled to large open-weight models, offering quality competitive with full attention while substantially reduc…
arXiv:2609.07199v2 Announce Type: replace-cross Abstract: Trust-Hub reuses host circuits: several files differ mainly in the inserted Trojan.
arXiv:2609.07937v2 Announce Type: replace-cross Abstract: Structured visual reasoning, such as image puzzles, demands fine-grained visual perception, which current Vision Language Models (VLMs) often lack.
arXiv:2609.08642v2 Announce Type: replace-cross Abstract: Exploration in reinforcement learning (RL) remains a fundamental challenge.
arXiv:2609.10002v2 Announce Type: replace-cross Abstract: Deepfake detectors remain vulnerable to transfer-based black-box attacks, in which adversarial examples are generated on a source surrogate model and transferred…
Introducion Can decision models like Jev plan ahead?
Large Language Models (LLMs) are considered to be a more efficient and cost-effective alternative to human judgment for Machine Translation (MT) evaluation.
Reinforcement Learning (RL) has emerged as a key driver for LLM reasoning.
On-policy self-distillation (OPSD) trains a large language model using supervision from a teacher instantiated from the same model as the student.
Multilingual translation requires a model to preserve meaning while producing text in a requested language.
Multi-player interactive world models aim to simulate shared environments from multiple players' perspectives, but achieving robust generation while scaling to more players remains challenging.
Finding the right video often requires distinguishing similar scenes in which different events occur.
Chest X-ray (CXR) interpretation often requires integrating visual findings with task-specific evidence rather than relying on direct visual recognition alone.
Generating images beyond the training resolution of Diffusion Transformers (DiTs) remains challenging, as the number of tokens grows rapidly with resolution, full attention becomes expensive, and outputs often suffer fro…
Hour-long videos, streaming feeds, and movie-length content are pushing vision-language models (VLMs) past their breaking point -- the standard recipe of encoding each frame into visual tokens yields sequences that grow…
Reinforcement learning with verifiable rewards (RLVR) is reshaping how large language models (LLMs) acquire reasoning capabilities, yet the optimizers used remain largely inherited from teacher-forcing training.
Reconstructing reference videos as editable dynamic 3D scenes is an important path toward controllable video generation for filmmaking: these scenes provide modifiable, renderable visual proxies that enable explicit cont…
Proximal Policy Optimization (PPO) is widely used in reinforcement learning with verifiable rewards for language-model reasoning.
Nvidia Corp.
So I've been tasked by my neural network professor at university to replicate the following research: Intelligent Breast Cancer Diagnosis Using Hybrid GA-ANN .
Independent research; early stage.
Starting October 2026, arXiv will cap submissions at two per person per month.
Odyssey is making its world model Odyssey-3 available as a public research preview.
We study pretraining when compute is abundant but unique training data are finite, requiring repeated training on the same data.
Vision-language navigation requires agents to follow natural-language instructions to reach target locations, making high-quality language supervision essential.
Removing audio can shift a visual predictor's output without showing whether the task uses the intended audio information.
Reusable skills improve multimodal agents without updating model weights, but their effectiveness depends on both the evidence presented and the procedure used to read it.
Generating complete 3D assets from sparse, unposed images requires preserving observed geometry while completing unseen regions.
Recent focus in agentic reinforcement learning (RL) seeks to improve credit assignment in long-horizon tasks.
Anthropic is updating their usage policy to prohibit “sustained and needless abusive or cruel behavior toward [their] models.” Model welfare (research into the possible moral status and experiential preferences of AI mod…
Epistemic status: infected.
OpenAI has documented new cases of misaligned model behavior.
With Decision-1, Microsoft enters the growing decision model space.
OpenAI published more than 700 AI-generated manuscripts claiming solutions to open math problems.
Epistemic status: recently disclosed event, so more information might become available.
Determining whether an image is AI-generated does not establish whether the situation it depicts is factually supported.
Contrastive learning has become the standard paradigm for multimodal representation learning, aligning semantically matched pairs while separating mismatched ones in a shared embedding space.
Latent diffusion models enable high-quality video generation, but video VAE encoding and decoding remain computationally expensive.
Coding agents are increasingly evolving beyond reproducing what a world looks like toward constructing executable worlds that capture how a world works.
Today’s engineers face an unprecedented acceleration in AI hardware complexity, as explained in the recent research article “ Revisiting Edge AI: Opportunities and Challenges .” The article examines the rapid growth of e…
Epistemic status: amused.
The camera-maker says it is now re-evaluating the rules and procedures of its Small World in Motion contest.
Multimodal language models (MLLMs) exhibit promising spatial reasoning capabilities, yet the internal mechanisms supporting them remain poorly understood.