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…
Yesterday
- PaperGlobal probabilistic forecasting of air pollution
Fine particulate matter (PM2.5) refers to particulate matter with an aerodynamic diameter of 2.5 micrometre or less. It comes from human activities, such as traffic and i
- PaperMITRA-lexicon: Lexica of attested translations from Sanskrit into English, Tibetan and Chinese
The standard Sanskrit lexica are monumental and indispensable, but they cite their attestations as abbreviated references to editions, without links to the digitized text
- PaperThe KV-Surgeon: Compensation-Aware Offline KV-Cache Compaction
Offline compaction of the key--value cache (KV-cache) reduces the cost of repeatedly querying a fixed context by constructing a smaller cache once and reusing it subseque
- PaperKeep the Lineages Alive: Diversity-Preserving SMC for Diffusion LLM Decoding
Inference-time sequential Monte Carlo (SMC) decoding can improve the reasoning accuracy of masked diffusion language models (diffusion LLMs) without post-training by resa
- PaperEvoSkill v2: Fully Agentic Skill Evolution from Benchmark Adaptation to a Stateful Evolver
EvoSkill v2 is a three-agent system that edits the instructions (skills) an agent is given, leaving its model and harness intact. The user starts a run by describing a be
- PaperTESS: LLM-guided Translation, Exploration, Simulation, and Search for Embodied Task Planning
In this work we focus on the problem of embodied task planning, which requires an agent to accomplish a complex task by separating it into atomic actions. Recent studies
- PaperOmniGround: Strengthening Omni-Modal Temporal Grounding via Attention-Consistency Training
Omni-modal large language models can jointly understand video, audio, and text, yet they remain weak at temporal grounding, a capability essential for real-world audio-vi
- PaperCondenseVLA: Learnable History Condensation for Efficient Multi-Frame VLA
Robot manipulation often depends on short-term cues - such as brief contacts, temporary occlusions, and intermediate object states - that are ambiguous in a single frame
- PaperMIRA: A Multimodal Illustrated Deep Research Agent for Controllable Reports
Deep research agents are increasingly capable of searching the open web and synthesizing evidence, yet they remain poorly suited to controllable report generation in mult
- PaperUtilityBench: Measuring Language Model Utility When Errors Have Different Costs
As language models are increasingly deployed in real-world scenarios with important outcomes, the impact of their mistakes often extends far beyond what correctness can c
- PaperSAPO: Self-Supervised Attention Policy Optimization for Improving Temporal Video Grounding in Vision-Language Models
Video vision-language models (VLMs) have strong semantic understanding, yet remain unreliable at precise temporal grounding. Existing gains from explicitly aligning video
- PaperMaestro: Agentic Formal Proof Development by Coordination
Lean is increasingly used to verify mathematical proofs and software produced by LLM agents, but writing formal proofs remains hard. Existing prover systems take a divide
- PaperLEAPS: Long-context Evaluation of Adaptive Pattern Learning and State Tracking
Long-context language models (LCLMs) power agents that act over long trajectories, from improving a codebase to running research experiments to forecasters that condition
- PaperLEAP: Accelerating ODE-based Diffusion Sampling with Optimal Linear Leaps
Diffusion models primarily rely on general-purpose ODE-based numerical methods for training-free accelerated sampling, but performance degrades with coarse time discretiz
- PaperSecure Agentic Coding through Counterexample-Grounded Feedback
As coding models and agent harnesses become more capable, reliable security verification is becoming a central bottleneck. Improving secure code generation requires a sig
- PaperFisherEdit: Fisher Information Guided Knowledge Editing for Large Language Models
Sequential knowledge editing in Large Language Models (LLMs) often leads to a degradation of general capabilities due to cumulative parameter interference. In this paper,
- PaperCALM: Consistency-Aware Logit Masking in Decoding Space for Mitigating Overthinking of Large Reasoning Models
Large reasoning models (LRMs) have achieved strong performance on challenging mathematical and scientific tasks through long chain-of-thought reasoning, but they often su
- PaperAn Analysis of Semantic and Spatio-Temporal Co-evolution for Edge Classification on Dynamic Text-Attributed Graphs
Dynamic edge classification on text-attributed Web graphs, such as review networks, community forums, and news-derived knowledge graphs, requires high quality, adaptive s
- PaperMulti-scale Fusion of Fast Vision Mamba and Foundation Model Features for Patch-Level Gleason Grading in Computational Pathology
Automated Gleason grading of prostate whole slide images (WSIs) enables faster and more consistent cancer risk stratification. However, it remains a challenging task due
- PaperOut-of-Distribution Detection in Continual Learning
Out-of-distribution detection in continual learning (OOD-CL) is highly challenging, as it requires (i) learning a sequence of tasks without catastrophic forgetting, and (
- PaperSWE-Residual: Evaluating Starting-State Robustness of Coding Agents
Software engineering (SWE) benchmarks are the primary way to measure the capabilities of coding agents: an agent is placed in a code repository or machine environment, gi
- PaperBudgeted Attack Scheduling for LLM Red-Teaming: The Roles of Static Priors, Semantic Guidance, and Online Feedback
As jailbreak attacks against large language models (LLMs) become increasingly diverse, red-teaming has come to rely on large libraries of jailbreak prompts and attack str
- PaperWhen Should AI Chime In? Benchmarking Timely Contribution of Proactive Agents in Multi-Party Chat
Proactive agents can support group collaboration by surfacing useful information without waiting to be asked, but even relevant contributions can be disruptive if poorly
- PaperMotor compound fault diagnosis using an attention-based cross-talk architecture
As physical AI increasingly relies on sensing to understand physical systems, reliable condition monitoring of industrial machinery has become more important. Motors are
- PaperManifold-Constrained Residual Adaptation with Frame-Adaptive Layer Aggregation for Speaker Verification
Large self-supervised speech models provide powerful representations for speaker verification, but full fine-tuning is expensive. Most conventional adapters insert small
- PaperRethinking Sparse-View 3D Gaussian Splatting: A Few-Shot Learning Perspective on Overfitting Prevention
Sparse-view novel view synthesis (NVS) is essential for AR/VR and real-time communication applications, yet remains challenging when reconstructing 3D scenes from limited
- PaperLearn the Interface, Not the Implementation: Output Representation Dominates Training Regime in LLM-Based RTL Generation
Large-language-model register-transfer-level (RTL) generation has concentrated on how to train the model: fine-tuning, continued pre-training, and reinforcement learning
- PaperAsynchronous On-Policy Self-Distillation
Unlike on-policy distillation (OPD), which depends on a separate teacher model, on-policy self-distillation (OPSD) leverages a single language model acting simultaneously
- PaperDeltaTrace: Efficient Signed Attribution for Reasoning Language Models
We study how words in the context support or oppose a language model's response and present DeltaTrace, a novel attribution framework that explains the effect of input to
- PaperLearning to Reason Efficiently with Interventional Step Credit
Large reasoning models often produce lengthy chain-of-thought (CoT) traces mixing useful intermediate steps with unnecessary ones. Recent methods explore step-level signa
- PaperVision-Language-Delta-Action: Learning Compact Deltas as Actionable Transition Interfaces for Robotic Manipulation
Robotic manipulation is not merely observation-to-action generation, but the realization of task-specified state changes in the physical world. Existing vision-language-a
- PaperResidual-Guided Adaptive Tucker Rank Allocation for Parameter-Efficient MCI Conversion Prediction
Allocating limited trainable capacity across convolutional layers is a central challenge in parameter-efficient fine-tuning (PEFT) of pretrained three-dimensional (3D) ne
- PaperCODA: Cohort- and Drift-aware Foundation Model for Multimodal Clinical Reasoning
Recent advances in multimodal foundation models have demonstrated strong performance across diverse clinical tasks. However, existing approaches predominantly operate at
- PaperBenefit-Targeted Routing and Bounded Revision for LLM-Based Evidence Screening in Manufacturing Supplier Discovery
An evidence-review system must allocate additional model judgments and control their use. We study these software decisions on 6,164 frozen manufacturing source-task pair
- PaperMinimum-Cost Robust Evidence Certificates for Horn Reasoning under Correlated Source Failures
A small justification for a rule-based conclusion may disappear when a source is withdrawn, and multiple derivations need not provide independent evidence. We study minim
- PaperActionRoPE: action as coordinates for spatially consistent control in planar-camera game world models
Game world models have made rapid progress toward real-time interactive generation. Yet action control is still predominantly implemented as feature conditioning, leaving
- PaperAdaptive Decoding Methods for Token-Efficient Reinforcement Learning
Rollout decoding affects both which trajectories are used for reinforcement learning with verifiable rewards (RLVR) and how many completion tokens are spent collecting th
- PaperAre Self-Evolving Agents Continual Learners?
Large language model agents are often deployed in environments where new knowledge, tools, and workflows keep arriving. Such an agent is therefore expected to adapt conti
- PaperStatistical Learning Theory for Direct Preference Optimization
Direct Preference Optimization (DPO) learns from pairwise preferences through a logistic objective whose score-difference parameterization follows the Bradley--Terry mode
- PaperArabic Financial NLP
Financial communication connects numerical accounts of economic activity with explanations of performance, responsibility and future expectations. Arabic financial natura
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.