AI news archive.
10,659 articles filed under Research, newest first, from the outlets listed on the sources page.
- Microsoft ResearchresearchImproving synthesis prediction of small molecules at scale with RetroChimera
Custom-made molecules are advancing medicine, materials, and agriculture, but producing them is slow and expensive. A new Nature paper highlights RetroChimera, a predictive model that helps accelerate chemical synthesis,…
- LessWrongresearchA class of statement between conjecture and theorem
Parts of the math community, such as Henry Cohn and Grant Sanderson, are arguing that proofs have been a proxy for understanding, and now that proxy is broken. This is a response to LMs generating incomprehensible proofs…
- LessWrongresearchMech Interp is a Verifiable Task
If we think parts of MLP0-MLP3 are computing [a sorting algorithm], we can replace those parts with [a sorting algorithm] and check reconstruction loss. [1] However, reconstruction loss is not enough. Suppose we replace…
- Hugging Face BlogresearchPruning LLMs Like a Physicist: Block Removal as an Ising Optimization Problem
Open-source model releases, tooling, and community updates.
- Import AIresearchImport AI 473: The US's superintelligence strategy; human brain in a mouse skull; and machine hermeneutics
Is the wall AI is hitting in the room with us right now?
- arXiv cs.AIresearchRBS-Attention: Radius-Bounded Sparse Prefill for Long-Context Large Language Models
arXiv:2609.20971v1 Announce Type: new Abstract: Long-context large language model inference is increasingly limited by prefill, where dense self-attention processes the entire prompt before generation begins. Sparse bloc…
- arXiv cs.AIresearchAttention-Aware Routing: Coupling Routing and Attention in MoEs
arXiv:2609.20974v1 Announce Type: new Abstract: In Mixture-of-Experts language models, the router typically selects and weights experts based on the token's hidden state, utilizing limited contextual information. We prop…
- arXiv cs.AIresearchCaLR: Causal Latent Revision for Robust Diffusion Reasoning
arXiv:2609.20981v1 Announce Type: new Abstract: Autoregressive (AR) models suffer from local greediness, while diffusion language models (DLMs) often lack the strict causal structure required for reasoning. To combine th…
- arXiv cs.AIresearchLoRA Enhanced Contrastive Learning with SAS Vision Transformers
arXiv:2609.21061v1 Announce Type: new Abstract: Automatic target recognition (ATR) with synthetic aperture sonar (SAS) supports advanced naval capabilities, but deep learning is constrained by scarce target imagery, back…
- arXiv cs.AIresearchDetecting Hallucination in LLMs: Tracing the Topological Signatures of Impaired Context Sharing
arXiv:2609.21096v1 Announce Type: new Abstract: In this work, we examine the topology of information flow patterns within attention graphs to effectively distinguish hallucinated from non-hallucinated responses. We analy…
- arXiv cs.AIresearchDecoupling Internal Representational Changes and Causal Importance in Fine-Tuned Large Language Models
arXiv:2609.21113v2 Announce Type: replace Abstract: Fine-tuning has emerged as a widely adopted approach for adapting LLMs to a variety of downstream tasks. However, how it reshapes their internal mechanisms remains poor…
- arXiv cs.AIresearchTinyCeNN-LM: Quality-Gated Conversion of Pretrained Attention with CeNN-Inspired Cellular-Recurrent Layers
arXiv:2609.21139v1 Announce Type: new Abstract: Replacing attention in a pretrained language model is a compatibility problem: a plausible substitute may alter representations expected by later layers. TinyCeNN-LM introd…
- arXiv cs.AIresearchClinician-Grounded Quality Assurance for AI-Assisted Psychiatric Intake
arXiv:2609.21149v1 Announce Type: new Abstract: Before patients can use AI-assisted psychiatric intake systems, health systems need practical ways to routinely evaluate these tools against their clinical standards for qu…
- arXiv cs.AIresearchImplicit Rule Induction with Test-Time Task Embeddings in ARC-like Tasks
arXiv:2609.21181v1 Announce Type: new Abstract: The Abstraction and Reasoning Corpus and related benchmarks evaluate whether AI models can solve novel reasoning tasks, but often leave unclear whether success reflects inf…
- arXiv cs.AIresearchInformation-Gain Rewards over Diversity-Pruned Tests: GT-Anchored Verifier Co-Training for Reliable Code Generation
arXiv:2609.21208v1 Announce Type: new Abstract: Self-play methods that co-train a single language model as both coder and test author promise to move code-generation RL beyond fixed test suites, but they suffer from two…
- arXiv cs.AIresearchAbility-Residual Decoupled Modeling for Affective Cognitive Diagnosis
arXiv:2609.21214v1 Announce Type: new Abstract: Cognitive diagnosis infers students' concept mastery from response logs. However, students' responses are not determined by mastery alone: non-cognitive factors such as emo…
- arXiv cs.AIresearchA Fully Differentiable Neuro-Soft-Symbolic Framework for Perceptual Task Planning
arXiv:2609.21221v1 Announce Type: new Abstract: Perceptual planning tasks require two key capabilities: accurately perceiving uncertain scenes and planning valid action sequences following logical rules. Conventional met…
- arXiv cs.AIresearchCogGym: Towards Large-Scale Comparative Evaluation of Human and Machine Cognition
arXiv:2609.21259v1 Announce Type: new Abstract: Understanding and modeling human intelligence are parallel goals shared by artificial intelligence (AI) and cognitive science. As AI systems grow increasingly capable, in w…
- arXiv cs.AIresearchPlaceReasoner-Beta: Reasoning-Driven Macro Placement and Benchmarking
arXiv:2609.21263v2 Announce Type: replace Abstract: Automated macro placement remains a fundamental challenge in VLSI physical design. Despite decades of research, existing approaches predominantly optimize hand-crafted…
- arXiv cs.AIresearchOffline Multimodal Large Language Models for Decision Support in Air Operations
arXiv:2609.21390v1 Announce Type: new Abstract: Air operations rely on complex rules, established procedures, and time-critical analysis under limited connectivity and strict security constraints. In such environments, a…
- arXiv cs.AIresearchGVPO++: Group Variance Policy Optimization for LLM Post-Training and On-Policy Distillation
arXiv:2609.21432v1 Announce Type: new Abstract: Post-training plays a pivotal role in enhancing the reasoning capabilities and task-specific expertise of large language models (LLMs). Despite recent advances in post-trai…
- arXiv cs.AIresearchLogicTrack: Auditing Reasoning Trajectories of Large Language Models with Formal Logic Solvers
arXiv:2609.21492v1 Announce Type: new Abstract: Chain-of-Thought (CoT) reasoning has been shown to improve the performance of large language models (LLMs), yet existing optimization methods largely rely on outcome-based…
- arXiv cs.AIresearchPolyBridgeBench: Benchmarking Multimodal LLMs for Physics-Grounded Bridge Design
arXiv:2609.21493v1 Announce Type: new Abstract: Multimodal large language models, or MLLMs, perform well at visual understanding and structured generation, yet these capabilities do not establish whether an engineering d…
- arXiv cs.AIresearchThe Communication Bottleneck: A Round-Trip Study of Tree-Structured Expression Serialization in Language Models
arXiv:2609.21509v2 Announce Type: replace Abstract: When language models reason in chain-of-thought or exchange free-text intermediates, they serialize structured information into natural language. How much tree-structur…
- arXiv cs.AIresearchDual-Interest Sequential Product Recommendation With Multi-Granular SSM
arXiv:2609.21548v1 Announce Type: new Abstract: Sequential recommendation aims to predict the next item a user will interact with based on their historical behavior. Advances in Transformers have significantly improved s…
- arXiv cs.AIresearchBeyond Accuracy: Centroid-Guided Contrastive Loss for Structured Fraudulent Job Posting Detection
arXiv:2609.21599v1 Announce Type: new Abstract: Fraudulent job posting detection aims to identify job advertisements that are corrupted either through fake content, misleading information, or negative intent, disrupting…
- arXiv cs.AIresearchReducing Barriers to Academic Support: Evaluating a Course-Specific RAG System for Addressing Help-Seeking Disparities in Higher Education
arXiv:2609.21600v1 Announce Type: new Abstract: Access to academic support is a key determinant of student success, yet students experience it unequally: some readily seek help from lecturers or tutors, while others hesi…
- arXiv cs.AIresearchCalibrating Teacher--Student Discrepancy for On-Policy Distillation
arXiv:2609.21619v1 Announce Type: new Abstract: On-policy distillation (OPD) improves reasoning models by learning the token-level discrepancy between a stronger teacher and an on-policy student. However, this discrepanc…
- arXiv cs.AIresearchOne Prompt Does Not Fit All: Self-Meta-Evolve for Personalized Information Extraction
arXiv:2609.21626v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed for enterprise information extraction (IE), where the same document must be reorganized differently for each user. Ex…
- arXiv cs.AIresearchAccelerating Dense LLMs via L0-regularized Mixture-of-Experts
arXiv:2609.21672v1 Announce Type: new Abstract: Large language models (LLMs) achieve strong performance but suffer from slow and costly inference. Existing acceleration methods often lead to noticeable performance degrad…
- arXiv cs.AIresearchGUARD: Natural Forgetting in Large Reasoning Models via Guided Answer-Reasoning Distillation
arXiv:2609.21677v2 Announce Type: replace Abstract: Recent advances in large reasoning models (LRMs) have made machine unlearning more challenging, as protected facts or unsafe rationales may surface in intermediate chai…
- arXiv cs.AIresearchListen Before You Speak: Response Planning from Listener Facial Reactions for Conversational Speech Generation
arXiv:2609.21683v1 Announce Type: new Abstract: Conversational speech depends on dialogue context and the listener's immediately preceding behavior. We propose ReACT-TTS, a two-stage framework that uses a one-second pre-…
- arXiv cs.AIresearchWorld Modeling in Transformers
arXiv:2609.21748v1 Announce Type: new Abstract: Behavioral failures can make a transformer appear to lack a world model even when it has learned faithful representations of its environment. We demonstrate this in TaxiGPT…
- arXiv cs.AIresearchECG Mirage: Revealing and Mitigating the Underutilisation of ECGs in Vision-Language Models for Clinical Prediction
arXiv:2609.21755v1 Announce Type: new Abstract: Emergency department (ED) decision-making relies on heterogeneous clinical information, including patient history, vital signs, laboratory results, and electrocardiograms (…
- arXiv cs.AIresearchLLM-Generated Feature Pools for Time Series Anomaly Detection
arXiv:2609.21801v1 Announce Type: new Abstract: We study how far a simple statistical pipeline can go on univariate time series anomaly detection under a strict selection protocol. The method extracts a small pool of sta…
- arXiv cs.AIresearchMIST: Multimodal Survival Prediction with Genomic-Guided Histology Attention
arXiv:2609.21811v1 Announce Type: new Abstract: Multimodal survival models can combine complementary prognostic information from whole-slide images and genomic profiles, but effective fusion remains challenging amid exte…
- arXiv cs.AIresearchEnterpriseVal: Quantifying the Efficacy, Reliability and Value of Generative AI in the Enterprise
arXiv:2609.21841v2 Announce Type: replace Abstract: Frontier language models now produce professional deliverables that expert graders judge to match human work on a substantial share of economically valuable tasks, yet…
- arXiv cs.AIresearchAutoRecLab: Describe the Experiment, Get the Code!
arXiv:2609.21863v1 Announce Type: new Abstract: Empirical evaluation is central to recommender-systems (RecSys) research, but turning experimental designs into executable code remains a manual and error-prone task. We pr…
- arXiv cs.AIresearchLearning Cardiac Features: ECG Biometrics Across Time and~Exercise
arXiv:2609.21962v1 Announce Type: new Abstract: Electrocardiograms (ECGs) carry subject-specific patterns enabling reliable individual discrimination, forming the basis of ECG biometrics. Beyond authentication, this para…
- arXiv cs.AIresearchA Lie Detector Test for Language Models: Reading Knowledge a Model Won't Reveal
arXiv:2609.21996v2 Announce Type: replace Abstract: Large language models can hold knowledge they do not report. A model may sandbag on a capability evaluation, or answer against what it internally knows, and its outputs…
- arXiv cs.AIresearchResNLS: An Improved Model for Stock Price Forecasting
arXiv:2312.01020v3 Announce Type: cross Abstract: Stock prices forecasting has always been a challenging task. Although many research projects try to address the problem, few of them pay attention to the varying degrees…
- arXiv cs.AIresearchdSTAR: Straggler Tolerant and Byzantine Resilient Distributed SGD
arXiv:2412.07151v1 Announce Type: cross Abstract: Distributed model training needs to be adapted to challenges such as the straggler effect and Byzantine attacks. When coordinating the training process with multiple comp…
- arXiv cs.AIresearchA Hybrid Computational Intelligence Framework for scRNA-seq Imputation: Integrating scRecover and Random Forests
arXiv:2511.16923v1 Announce Type: cross Abstract: Single-cell RNA sequencing (scRNA-seq) enables transcriptomic profiling at cellular resolution but suffers from pervasive dropout events that obscure biological signals.…
- arXiv cs.AIresearchMaking Latent Evolution Explicit: Operator-Structured Transitions for World Action Models
arXiv:2608.27259v1 Announce Type: cross Abstract: World Action Models (WAMs) augment robot policies by predicting how task-relevant scene states may evolve under interaction. Recent WAMs increasingly perform such predict…
- arXiv cs.AIresearchReinforcement learning for post-coronagraphic wavefront control
arXiv:2609.20880v1 Announce Type: cross Abstract: Direct imaging of exoplanets is limited by the extreme contrast between the star and the planets, which is mitigated using a coronagraph. However, optical aberrations cau…
- arXiv cs.AIresearchSpaceDiffusion: Over-the-Orbit Diffusion for Space Generate-and-Forward Communications
arXiv:2609.20899v1 Announce Type: cross Abstract: Satellite communications are an essential component of sixth-generation (6G) mobile networks, which provide ubiquitous connectivity for global services. However, the sate…
- arXiv cs.AIresearchBio-MF: Low-Latency and High-Fidelity EEG-to-fNIRS Cross-Modal Generation for Hybrid Motor-Imagery Brain--Computer Interfaces
arXiv:2609.20904v1 Announce Type: cross Abstract: Hybrid motor-imagery brain-computer interfaces (MI-BCIs) combining EEG and fNIRS can outperform EEG-only systems by exploiting complementary electrophysiological and hemo…
- arXiv cs.AIresearchTrustworthy FinAInce: Unpacking How AI-Mediated Financial Advice is Judged
arXiv:2609.20989v2 Announce Type: replace-cross Abstract: As generative AI is increasingly used as a source of personal financial guidance, understanding how people appraise such advice is important for supporting approp…
- arXiv cs.AIresearchPhysically Based Rendering in the Latent Space
arXiv:2609.21054v1 Announce Type: cross Abstract: Image diffusion models have shown impressive image generation capabilities but are often hard to control, in contrast to classical computer graphics pipelines such as phy…
- arXiv cs.AIresearchHow Much of a Real Workload Can LLM-Generated GPU Kernels Actually Reach?
arXiv:2609.21058v1 Announce Type: cross Abstract: Language models can now write GPU kernels that outperform PyTorch. We evaluate five model configurations on KernelBench level 1 and find that a frontier model produces co…