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…
Monday 19 October
- PaperTempoMoE: Identifying and Steering Fast-Slow Thinking Experts for Efficient Multimodal Reasoning
Multimodal Mixture-of-Experts (MoE) reasoning models rely on long chain-of-thought (CoT) for complex tasks, yet often overthink easy inputs, increasing token cost and lat
- PaperInternalizing Chain-of-thought into Looped Transformers
Chain-of-thought (CoT) enables constant-bit-size transformers to perform general-purpose computation through generated tokens (Li and Wang, 2025a), whereas looped transfo
- PaperFederated Community Detection in Bipartite Networks
We study federated spectral estimation when a large matrix is horizontally partitioned across servers that cannot share raw data. We propose FLICKER, a target-specific gr
- PaperProcedural Memory for Language Agents: A Neurosymbolic Perspective on Explicit Goal Structure
Large language models remain unreliable on long-horizon tasks requiring procedural reasoning. We argue that a key cause is the absence of explicit procedural memory: acce
- PaperGraph-to-Table Interfaces Control Relational Generalisation
Graph-to-table systems combine three design choices: an encoder that maps relational evidence to feature rows, a context constructor that selects labelled examples, and a
- PaperMap-Distribution Mixture-of-Experts for Multi-Agent Pathfinding
Designing capable neural policies for multi-agent pathfinding (MAPF), which map local observations to action distributions, represents an important challenge in multi-age
- PaperNIOCIS: Typed-Decision Next-Hop Routing with Node-Conditioned Option Spaces for Tool-Use Agents
Tool-use agents pay per decision: at each hop a language model re-reads the state and thinks for seconds, though its actions are finite and decisions recur. We present NI
- PaperAuditor-Assisted Summary-Channel Verification for Hosted LLM Identity Substitution
Hosted LLM services increasingly expose model identity as a product claim, but external users and auditors often cannot inspect which model configuration served a request
- PaperClueFlow: Learning Long-Horizon Search through Attributed Research-State Transitions
Long-horizon search requires agents to acquire relevant evidence and integrate it into an evolving research state. Existing methods maintain research states to guide expl
- PaperGraphEvoResearcher: Graph-Aware Training-Free Self-Reflective Reasoning for Cost-Bounded Multi-Hop Question Answering
Multi-hop question answering (QA) requires models to chain intermediate conclusions while remaining cost-aware. Existing training-free self-reflective protocols (generate
- PaperOn the Benefits of Uncertainty Estimation for Species Classification: A Case Study on Optimizing Expert re-Annotation
Automated identification of diatoms from microscopic images is a cornerstone of large-scale freshwater biomonitoring, yet the high diversity of species and strong class i
- PaperCorrectness-Dependent Asymmetric Target Distributions for Self-Distillation Policy Optimization
Self-distillation policy optimization provides dense token-level supervision for LLM post-training through feedback-conditioned self-teachers. However, directly matching
- PaperGLOBE: Geometry-Led Online Behavioral Early Exit via Unit-Sphere Trajectories
Chain-of-thought (CoT) reasoning can improve problem solving, but models often keep generating after the correct answer is already reachable; the extra steps raise servin
- PaperReconstruction and Discrete-Event Simulation Assessment of an Analytical
This article presents an analytical-DES benchmark for intra-aisle robotic picking in automated warehousing. The investigated cycle combines horizontal shuttle travel, tot
- PaperBehavioral Probes for Information Flow in LLM Swarms
Most existing approaches to LLM swarm optimization are utility-driven, focusing on final task utility while leaving the processing, integration, and reliance of informati
- PaperToken-Set Choice Confounds POPE: A Systematic Audit of Yes/No Extraction in VLM Hallucination Evaluation
We set out to reproduce a recent hallucination-mitigation result on the POPE benchmark. The LLaVA-1.5-7B baseline we measured, 82.21 F1 on the adversarial split, sat 1.21
- PaperABACUS: Program-Guided Multistep Reasoning over Frozen Judgment Models
Judgment models answer semantic questions by scoring a finite set of candidate outcomes. Can reusable programs turn these local decisions into powerful multistep reasonin
- PaperPaceVLA: Adaptive Temporal Action Quantization in Vision-Language-Action Models
Fast and reliable manipulation is crucial for practical robot deployment. Although Vision-Language-Action (VLA) models have recently shown remarkable progress as generali
- PaperHow to get the best and fairest performance out of your ASR system using activation steering
Activation steering for ASR systems is an underexplored technique in improving both ASR performance and demographic fairness. We investigate two forms of activation steer
- PaperHORIA: 4D Human and Object Reconstruction from a Monocular Video with Interaction-Aware Re-Rendering
Joint 4D reconstruction of a human and object from a monocular video is essential for understanding how people interact with their environment. While recent methods have
- PaperEmbodiedWorld-200K: Toward Embodied World Agents via Embodied-Planning Dataset and Interactive World Models
Building embodied agents that can perceive, reason, and act across diverse 3D worlds is a central research direction toward artificial general intelligence. Yet most exis
- PaperProductive State-Space Exploration for Multi-turn RL in LLM Agents
Reinforcement Learning (RL) for Large Language Model (LLM) agents in multi-turn, long-horizon environments remains challenging due to inefficient action selection and rep
- PaperCXBench: A Benchmark for Process-Compliant LLM Agents in Regulated Customer-Experience Workflows
Tool-using language agents increasingly perform regulated customer-service workflows, where a correct final state is insufficient: agents must also provide disclosures, o
- PaperAdaExploreBench: Benchmarking LLM Agents for Proactive Exploration and Test-time Adaptation in Evolving Environments
Large Language Model (LLM) agents are increasingly deployed in unfamiliar and evolving environments, requiring them to proactively explore, understand, and adapt to envir
- PaperOrderGPT: Generation Order as a Learnable Modeling Choice
Generative modeling of discrete data has two popular paradigms: autoregressive models such as GPT, which factorize a sequence in a left-to-right (L2R) order, and masked d
- PaperClaim Laundering: When Agent Decision Models Trust Records Over Reality
Agent decision models select actions in a single forward pass from inputs that combine environmental observations with the agent's own record of previous actions. When an
- PaperPolicy Search in Code Space for Multi-Agent Pathfinding
Developing coordination policies for complex multi-agent systems relies on either labor-intensive algorithm design or opaque task-specific reinforcement learning. With re
- PaperTRACE: Training-aware Robustness and Challenge Evaluation for Text-Vision Embedding Models
Existing benchmarks for text-vision embedding models report aggregate scores that obscure whether performance comes from general capabilities, task-specific adaptation, o
- PaperCoASFL: Coupled Consistency Optimization for Asynchronous Split Federated Learning
Split Federated Learning (SFL) has emerged as a promising paradigm for training large-scale deep models on resource-constrained edge devices. Although asynchronous SFL al
- PaperSpeech LLMs That Breathe: Modeling Non-Verbal Vocalizations in Dialogue
The user experience of speech interaction models has improved, benefiting from the modeling of paralinguistic attributes and advances in speech reconstruction paradigms.
- 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
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.