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
- PaperKiranaBench: Can a Language Model Run a Neighbourhood Shop?
Large language model (LLM) agents are increasingly evaluated on long-horizon tasks, including autonomously running a business. Existing benchmarks for this setting are al
- PaperTowards Hyperparameter Transfer for Differentially Private Optimization
Scaling laws and hyperparameter tuning remain central challenges in training large-scale models, particularly under differential privacy (DP), where optimization is furth
- PaperSink-Sparse Hybrid Attention for Efficient Inference in T2I/T2V Diffusion Transformers
Diffusion Transformers (DiTs) have become a common backbone for high-quality text-to-image and text-to-video generation, but repeated dense self-attention remains a major
- PaperDiffusionRVGE: Reinforcement Learning via Regression-Based Value Gradient Estimation
Reinforcement learning improves diffusion models using rewards on generated images, but repeated denoising and gradient estimation make training expensive. We introduce \
- PaperNL2SQL with Iterative Self-Refinement
Bridging the gap between human intent and machine logic remains a critical challenge in data access for non-technical users, yet Large Language Models (LLMs) remain unrel
- PaperANCHOR: Audio-Visually Grounded Chain-of-Thought Reasoning Benchmark
Multimodal large language models (MLLMs) perform well on audio-visual question answering, but correct answers do not necessarily imply that their stated reasoning is grou
- PaperWhat Shapes Brain Alignment of Large Language Models during Dialogue? Insights from Language Production and Comprehension
Brain alignment of large language models (LLMs) offers a way to investigate representational similarities between LLMs and the human brain during language processing. Whi
- PaperSAFE-Mem: Secure Agentic Memory with Fine-Grained Authority and Governance-Aware Retrieval
Large language model (LLM) agents increasingly rely on persistent memory to support long-term reasoning and personalized interactions. However, information collected from
- PaperStabilizing Illumination Conditioning in SSM-Based Low-Light Image Enhancement with Bottleneck Prompt Sidecars
Low-light image enhancement (LLIE) requires more than brightness amplification because real low-light images often exhibit spatially varying illumination, amplified noise
- PaperQuery-adaptive Recurrent Tokenization
Visual information worth extracting from an image and the token budget it warrants depend on the text query. Yet modern vision and vision-language models largely encode i
- PaperOn the tradeoff between robustness and geometric accuracy in adversarial training
For non-parametric binary classification in the presence of an adversary, we prove an optimal quantitative estimate for adversarial classifiers controlling geometric accu
- PaperRecognizing Atari and Assessing Sente: Controlled Evaluation Tasks for Language-Based Go Agents
Domain terminology provides concise descriptions of game states and strategic relationships, but whether game-playing language models can accurately recognize these conce
- PaperMambaAct: Efficient Mamba Action Experts for Flow-Matching Vision-Language-Action Models
Vision-language-action (VLA) models have shown strong promise for generalist robotic manipulation, but their inference cost remains a major bottleneck for real-time contr
- PaperLarge Diffusion Models Need More Than EMA
Large-scale diffusion models are commonly trained with a constant learning rate (LR) and exponential moving average (EMA), despite the strong performance of LR decay and
- PaperAligning Language Models Towards Counterfactual Invariance
Small variations in prompt characteristics can meaningfully alter the semantics, tone, and contextual assumptions of large language model outputs. Such characteristics ca
- PaperBeyond Surface Cues: Robust LLM-Generated Korean Text Detection
As large language models (LLMs) generate increasingly fluent text, the need for reliable detection of LLM-generated content has grown substantially. However, existing res
- PaperMany Biases, One Circuit: Post-Training Tunes a Pretrained Cue-Routing Mechanism
Language models often abandon a correct answer when the prompt contains a cue, a hint toward a wrong option such as "I think the answer is B." Sycophancy and related bias
- PaperASR-Style Transcript Normalization Removes Useful Pragmatic Signal for Dialogue Act Classification
Automatic speech recognition (ASR) pipelines often normalize transcripts by removing filled pauses and punctuation and expanding colloquial forms, potentially discarding
- PaperConformal Policy Selection: When to Deploy AI Decisions for Targeted Intervention
Artificial-intelligence (AI) policies are increasingly used to make consequential decisions in medicine, finance, education, and public services, yet deploying them respo
- PaperDICL-Qwen3VL: Decoupled Confidence Calibration for Interpretable Workwear Detection
Poor illumination and occlusion obscure clothing cues in indoor work sites, while diverse clothing styles complicate workwear compliance judgments. Although vision-langua
- PaperMultiple Turns, Short Horizons: Measuring Effective-Horizon Compression in Jailbreaks
Multi-turn jailbreaks use feedback from a victim large language model to adapt their queries over several turns. However, once an effective trajectory has been found, it
- PaperScalable Levenberg-Marquardt Training Framework for Deep Learning
The Levenberg-Marquardt (LMA) algorithm is a widely used nonlinear least-squares solver known for its rapid convergence. For small-scale neural networks, LMA provides bet
- PaperSep-Latent: Separator Tokens as Natural Compression Anchors for Implicit Reasoning
Large Language Models (LLMs) have demonstrated remarkable success in complex reasoning through explicit Chain-of-Thought (CoT), but the associated computational overhead
- PaperODSS-Net: Orthogonally Decoupled Shared-Specific Representations for Multi-Modal Object Re-Identification
Multi-modal object re-identification (ReID) leverages complementary information from heterogeneous sensors. Cross-modal alignment and fusion remain challenging. Existing
- PaperMaskMerge: Structure-aware Token Merging for Efficient Instance Segmentation
Token merging improves the efficiency of Vision Transformers by combining redundant tokens, but existing methods largely rely on feature similarity to determine which tok
- PaperWhere's the Indirect Evidence? Investigating Grammatical Generalization with Influence Functions
Language models generalize beyond their training corpus to learn linguistic phenomena (Patil et al., 2024; Misra and Mahowald, 2024), showing that there exists indirect e
- PaperDynamical Kernel Attention: Estimating the Present from a Record of the Past
Standard self-attention compares tokens by similarity but does not account for how much of a past state survives to the present. We introduce Dynamical Kernel Attention (
- PaperReward Engine: Reward-Centric Self-Evolution for Open-Ended Tool Agents
Open-ended tool agents can complete the same objective through different tool paths, and their quality depends jointly on the interaction trace, environment state, and fi
- PaperCOMET: Decoupled Distillation, Routing, and Capacity Control for Task-Agnostic Continual Vision--Language Learning
Vision-language models (VLMs) such as CLIP retain zero-shot recognition ability, but their open-world use often requires task-agnostic continual learning: tasks arrive se
- PaperFederatedBytes: Tokenizer-Free, Byte-Level Small Language Models for Efficient Multimodal Federated Learning
Federated Learning (FL) is a powerful machine learning framework that allows building a global model from the contributions of multiple, distributed clients, while ensuri
- PaperA Feature Selection Layer Approach for Multi-Class Classification on Neural Networks
In the age of data-driven decision-making, deep learning models have become powerful tools for uncovering patterns and making predictions that influence many aspects of s
- PaperWhen to Forget: Risk-Controlled Context Adaptation for Long-Horizon Agents
Long-horizon agents learn from failure, but the value of a failure record can change as execution progresses. We study when retaining, compressing, or removing the same h
- PaperHAPACT: A Benchmark For Human-Centric Physical Impact Localization in Movies
Physical reasoning about humans in videos has largely focused on everyday interactions, where contact, pressure, pose, and motion support embodied perception and contact-
- PaperUnified Multiparadigm Fusion Intelligence for Rare Disease Diagnosis
Rare diseases (RDs) affect an estimated 300 million people globally, leaving patients to navigate a protracted diagnostic odyssey constrained by clinical scarcity and fra
- PaperCompetence-Based Evaluation of Logical Reasoning in Large Language Models
Recent advances in large language models (LLMs) have brought impressive performance across diverse tasks; however, shortcomings remain in logical reasoning, including inc
- PaperBengali Hallucination Detection with Retrieval and Programs: A System Study
Bengali hallucination detection must distinguish unsupported factual claims from incorrect reasoning, often without a supplied reference passage. We present and character
- PaperWhat Accuracy Hides In Learned Transformer Programs
Transformer Programs (TP) (Friedman et al., 2023) constrain a Transformer's architecture so that its learned computation can be extracted as readable Python code. TP expo
- PaperNLData2Opt: Benchmarking Parameter Derivation and Prediction for Modeling Optimization Problems from Natural Language and Data
Formulating optimization problems from raw inputs of problem descriptions and data is time-consuming and costly. While Large Language Models (LLMs) offer a promising way
- PaperBatched Contextual Reinforcement II: Does RLVR Need Long Rollout Windows?
Long rollout windows make reinforcement learning with verifiable rewards (RLVR) expensive, yet simply shortening them can remove the correctness signal: when every single
- PaperLearning to Be Guided: Shaping Latent Geometry for Classifier-Free Guidance
Classifier-free guidance (CFG) is a standard component of conditional diffusion models, and guided generation performance has become the \textit{de facto} measure of stat
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.