New
Everything new in AI as it appears: launches announced by the labs, brand-new models, datasets, papers and open-source tools. Checked every minute or two. Launches feed · Trending · News
Live now
- Connecting…
Friday 16 October
- PaperFlashReFocus: Interactive Image Refocusing in Seconds
Single-image refocusing changes the focal plane and depth of field of a photograph after capture. It is inherently interactive: users try many focal points and blur stren
- PaperLearning angles for quantum approximate optimization
The Quantum Approximate Optimization Algorithm (QAOA) and its variants are leading algorithms to help solve challenging combinatorial optimization problems. QAOA maps the
- PaperThe Optimal Ranking Tradeoffs Between Two Ranking Scores in Two-Class Classification
The accuracy, true negative rate (negative class recall), true positive rate (positive class recall), negative predictive value (negative class precision), positive predi
- PaperDistributed Performance Boosting through Neural Control for Plug-and-Play Networks
We address the problem of improving the performance of pre-stabilized networked systems subject to plug-and-play (PnP) operations, namely additions or removals of subsyst
- PaperCoTA++: Understanding the Repeat Curse in dMLLMs from an Information Flow Perspective
Diffusion-based multimodal large language models (dMLLMs) decode by iterative denoising with bidirectional attention, which precludes the standard autoregressive key--val
- PaperData-Efficient Classifier Pretraining Through Diffusion Models
Machine learning with limited data is susceptible to overfitting, especially with modern deep neural networks. Prior to the introduction of AlexNet, reconstruction-based
- PaperI2V-DETACH: Source Grounding Detachment for Unauthorized Image-to-Video Generation
Recent diffusion models have advanced image-conditioned video generation, but their accessibility raises risks of unauthorized manipulation. Image immunization has emerge
- PaperAnnotrace: A Workbench for Step-Level Annotation of Agent Traces
Every study of why LLM agents fail begins by labelling traces by hand, and every such study builds its own throwaway tool. Observability platforms record agent traces but
- PaperXiaomi-Lens-0 Technical Report
Multimodal large language models (MLLMs) answer questions about whole images well, yet they still struggle with fine-grained region understanding. A key reason is that te
- PaperVerbalising Model's Computation for Chain-of-Thought Faithfulness Detection
Current Chain-of-Thought (CoT) verification methods detect reasoning faithfulness from model outputs or static activations, but are limited in explaining how unfaithfulne
- PaperDeDiCa: A Scalable Deconfounding Discrete Causal Generative Model
We introduce DeDiCa, a practical framework for efficient causal inference with discrete variables and hidden confounding that revisits classical probabilistic modeling th
- PaperNestedVLA: Learning to Consolidate and Generate Skills for Vision-Language-Action Models
Vision-language-action (VLA) models can learn a wide range of robotic skills, but combining separately trained skills remains challenging. The original training data may
- PaperAgentic Image Generation in the Wild
Agentic image generation pairs an image generator with a search agent that retrieves references from the web, extending generation beyond the generator's training data. R
- PaperBeyond Marginal Influence: Interaction-Aware Memory Selection for LLM Agents
LLM-agent memory selection often uses retrieval rankings based on record relevance or individual influence. Such rankings cannot identify sufficient subsets under redunda
- PaperADT: All-Atom Diffusion Tokenizer for 3D Molecular Structures
Discrete structural tokenization provides a promising route to autoregressive 3D molecular generation. Yet, existing tokenizers face a trade-off between compact represent
- PaperSCALE: Improving Guidance-Free Visual Generation via Self-Contrastive Alignment for Likelihood Estimation
Classifier-free guidance (CFG) is essential for improving sample quality in visual generation, but it incurs substantial sampling overhead. Existing guidance-free approac
- PaperExpand-and-Prune: Test-Time Candidate-Space Adaptation for End-to-End Autonomous Driving
Candidate-based end-to-end driving planners reason over a finite set of trajectory hypotheses. However, for sparse planners, a limited candidate set may provide insuffici
- PaperReasoning Models Can Control Their Chains of Thought When They Tell Themselves To
Chain-of-thought (CoT) controllability, the ability of reasoning models to control properties of their CoT, is consequential for both their usefulness and reliable oversi
- PaperBeyond Reward Scoring: Online Multi-Agent Preference Learning for Multimodal Response Generation
Multimodal preference alignment often follows a score-based RLHF pipeline: a reward model is first trained to learn human preferences, then used to score on-policy respon
- PaperSample, Mix, or Verify? Allocating Test-Time Compute under Imperfect Verifiers
A common way to make language models and agents more accurate is to spend more compute at inference time: generate many candidate solutions and submit the one a verifier
- PaperIgnored, Not Refused: What Low Prompt-Injection Success Rates Hide in Small Tool-Using Agents
Tool-using agents read untrusted external content, which exposes them to indirect prompt injection (IPI), where hidden instructions hijack the agent's tool calls. Benchma
- PaperLLM Evolution in a Simple Simulated Market
Arguments that AI systems will evolve in harmful ways are largely made in the abstract. We provide a concrete empirical example. We simulate simple markets consisting of
- PaperPreventing Data Hallucinations in Agentic AI for Optical Network Troubleshooting
An agentic AI system for automated troubleshooting in optical communication networks is demonstrated that integrates data references into the agent architecture to preven
- PaperFLARE: Physics-Grounded Evaluation of Language-Model Agents for Feeder Restoration with Degraded Observations
Restoring service after distribution-grid faults requires decisions from incomplete and conflicting information while respecting electrical constraints. Addressing this n
- PaperLonGaussian: Tracking Foundation Priors for Long-Context Feedforward Gaussian Reconstruction
Reconstructing high-quality, renderable 3D scenes from long videos is essential for robotic perception and embodied intelligence. Many feed-forward Gaussian reconstructio
- PaperWho Pays for Efficient Inference? Confidence-Based Small-to-Large LLM Routing Across Tasks and Languages
Small-to-large language model routing can reduce inference cost by escalating difficult inputs while retaining easier ones on a smaller model. Its success, however, depen
- PaperCan the Parts Fool the Test? Counterfactual Pairing Cycles for Relational OOD
Relational out-of-distribution errors are easy to describe and hard to evaluate cleanly. An image may be natural, a caption may be fluent, and all mentioned objects may b
- PaperThink More or Read More? A Token-Budget Theory of Reasoning with Shared Context
Reasoning systems increasingly improve answers by incorporating additional context into the model's input, from multi-agent debate, where agents read their peers' respons
- PaperMGE-PO: Entropy-Aware Credit Assignment for Mathematical Reasoning
GRPO assigns the same group-relative advantage to equally rewarded responses within a question, leaving their generation uncertainty unused. We introduce MGE-PO, centered
- PaperAnisotropic Representation Dynamics in Transformers
Small differences between internal representations can shrink or grow as they pass through a Transformer layer, affecting how information is preserved and how sensitive t
- PaperResponse-Informed Value Estimation for Cost-Aware Multi-Turn LLM Routing
Multi-turn LLM routing selects a model at every turn before its response is available, yet task success is revealed only when the interaction ends, leaving each intermedi
- PaperKingfisher: Fast Personalized Visual Autoregressive Generation via Scale-Aware Prompt-Conditioned Scale Decomposition
Personalized image generation has been extensively studied in diffusion models, often relying on subject-specific optimization of model weights, textual embeddings, LoRA
- PaperX-Splat: Unified Gaussian Splatting for Joint RGB and X-ray 3D Reconstruction
Jointly reconstructing RGB and X-ray provides new insights by connecting external appearance with internal structure, enabling a more complete understanding of real-world
- PaperMultiAgent-OPD: End-to-End Training of Hierarchical Multi-Agent Systems with On-Policy Distillation
In a hierarchical multi-agent system, a Leader assigns tasks and subagents carry them out. Jointly training the Leader and the subagents is difficult because a final answ
- PaperRAP: A Dataset for Paper-to-Poster Generation via Declarative Markup from Human-Crafted Exemplars
Making a conference poster is visual coding in miniature: an entire paper must be compressed onto a single page, which exercises summarization, visual design, and code im
- PaperCharacterising and Analysing Retrieval-Augmented Generation Techniques
The advent of Large Language Models (LLMs) across many application domains has increased the need for Retrieval-Augmented Generation (RAG) to reduce hallucinations and im
- PaperReLaDrift: Recurrent Language Generation via Drifting for Test-Time Scaling
Drifting Models generate a sample with a single function evaluation, making them attractive for fast parallel language generation, but their one-step formulation does not
- PaperProcess Reward Modeling with Reliability- and Conservatism-Aware Bayesian Belief
Process Reward Models (PRMs) play a central role in test-time scaling for large language model (LLM) reasoning. However, PRMs may provide inaccurate process rewards for t
- PaperqGAMMA: A Framework for Optimal DNN Mapping on Multi-Precision Accelerators
This work describes qGAMMA, a flexible framework for exploring and optimizing the mapping of mixed-precision Deep Neural Network (DNN) models onto general-purpose spatial
- PaperMLLM Frame Subset Ensembling for Audio-Visual Video QA and MLLM-based Reranking for Ad-hoc Video Search in TRECVID 2025
This paper presents the overview of the runs related to the Ad-hoc Video Search (AVS) and Video Question Answering (VQA) tracks of TRECVID 2025 on behalf of the CERTH-ITI
Headlines and links come from the labs' own blogs, Hacker News and the GDELT news index, and from the sources our index already follows. We show a short excerpt and always link to the original. A launch reported by a news site rather than the lab is marked “Reported” until the lab itself announces it.