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
- PaperToPA: Block-wise Toeplitz Adaptation for Expressive and Efficient Fine-Tuning
Parameter-Efficient Fine-Tuning (PEFT) has emerged as a prevalent strategy for adapting large pre-trained models. Among PEFT techniques, reparameterization-based methods,
- PaperCooperation Without Adaptation: LLM Agents in a Collective-Risk Dilemma
Language-model agents are increasingly deployed to act on behalf of people in settings where individual decisions shape shared outcomes. We examine whether five productio
- PaperIdentify, Classify, Act: Per-Instruction Controlled Compliance for LLMs over External Data
LLMs over external data face a per-instruction tension: a single document or tool return often interleaves legitimate directives with adversarial prompt injections, and t
- PaperProtoGTX: Prototype-Aligned Graph Transformer for Explainable Whole-Slide Image Analysis
Deep learning has achieved strong performance in computational pathology, but explaining whole-slide image (WSI) predictions remains challenging. Existing explanation met
- PaperLook Back, Correct Forward: Error Feedback Calibration for Time Series Forecasting
Time series forecasting models are increasingly deployed in continuously evolving environments. After a forecast is issued, future observations gradually arrive and revea
- PaperShadowFPT: Backdooring Federated Prompt Tuning via Shadow Triggers
Federated Prompt Tuning (FPT) adapts large vision--language models by freezing the pretrained backbone and optimizing only lightweight prompt parameters across clients. A
- PaperMS-Eval: Benchmarking Sub-Agent Delegation and Orchestration in MCP-Intensive Working Scenarios
LLM agents are increasingly integrated into real-world works, yet they must handle diverse domain-specific tools and complex multi-sub-task problems that sequential tool
- PaperEvo-B&B: Behavior-Aware LLM-Guided Joint Evolution of Branching and Node Selection Policies for MILP
In branch-and-bound for Mixed-Integer Linear Programming (MILP), branching and node selection are two critical and tightly coupled decisions, yet most existing learning-b
- PaperUncertainty-Aware Budget Allocation for Efficient LLM Tree Search
Tree search enhances multi-step reasoning in large language models (LLMs), yet prevailing methods expand every step with a fixed budget, irrespective of the marginal util
- PaperSample-Efficient Reinforcement Learning for Policy Improvement via Flow-Reversed Action Anchors
Generalist robot policies offer strong behavioral priors, but achieving deployment-level reliability and throughput remains difficult. Reinforcement learning (RL) can imp
- PaperMeasurement-Adaptive Light-Cone Transform for Robust Non-Line-of-Sight Imaging
Practical non-line-of-sight (NLOS) measurements are affected by noise and deviations from idealized light transport, which can degrade reconstruction with conventional li
- PaperBenchmarking and Enhancing Agentic Causal Discovery
LLM agents can now run causal discovery algorithms on a dataset and report what comes out. Whether they do more than that, such as noticing where an algorithm went wrong
- PaperDinoMUSE: A DINOv2-guided Framework for Unsupervised Lateral Motion Estimation in Ultrasound Elastography
Quasi-static ultrasound elastography (USE) is a non-invasive imaging method for assessing soft tissue mechanical properties. Limited by low resolution, low sampling frequ
- PaperVariational and Decomposed method for Mitigating Bimodal Bias in Robust Visual Question Answering
Visual question answering (VQA) models are known to suffer from the bias issue, which refers to overfitting the regularities of frequent patterns. Previously, researchers
- PaperVTrajEmbed: Aligning Text with Video Object Trajectories via Spatiotemporal Embeddings
Fine-grained alignment between text and video object trajectories is a core challenge in multimodal understanding. Existing embedding models excel at global retrieval, ye
- PaperThe Reliance Hypothesis: Chain-of-Thought Faithfulness Rises as Language Resource Level Falls
Chain-of-Thought (CoT) faithfulness matters for monitoring, explaining and safely deploying large language models, yet it has been studied mostly in English. Languages di
- PaperToo Emotional to Be Fake? Intra-Utterance Emotion Shifts Expose Failure Modes in Speech Deepfake Detectors
Expressive speech synthesis can now change emotion within a single utterance, yet its impact on deepfake detection remains unclear. We introduce EmoShift, a benchmark com
- PaperPartial-Revelation Panel Forecasting: Predictive Information Gain, Allocation, and Coarsening-Consistent Operators
We study partial-revelation panel forecasting: given $k$ of $n$ annotator votes on the previous dialogue turn, predict the full count distribution of the next turn's pane
- PaperWorld Action Critic (WAC) Model: Joint Foresight and Criticism for Policy Learning
World models have shown considerable promise in sequential decision-making by anticipating the consequences of actions and providing predictive foresight for policy learn
- PaperVISTA: A Multimodal Egocentric Benchmark for Goal-Oriented Perception and Assistance to Blind and Low-Vision Users
Blindness and low vision limit many people's ability to complete daily tasks, motivating AI assistants that provide useful guidance. Yet, existing benchmarks do not adequ
- PaperCausal Edit Serialization
Standard autoregressive language models generate text sequentially, but revision requires referring back to tokens in the input context or those already generated. Causal
- PaperReplay Pruning and Few-Bit Integer Inference for Hardware-Efficient Speed-Sign Recognition
Speed-limit sign recognition on an automotive camera system-on-chip (SoC) must fit a detector and a classifier (the reader) into the memory, arithmetic, and energy budget
- PaperWatermarkability: Measuring and Improving Language-Model Compatibility with Logit-Based Watermarks
Language-model watermarks can help identify model-generated text, encode provenance information, and detect post-generation edits. A broad class of logit-based watermarks
- PaperOn the Position Bias of Large Language Models: A Comprehensive Study
Recent studies have shown that position bias remains a critical vulnerability in large language models (LLMs), undermining both the integrity of multiple-choice evaluatio
- PaperCompression Precedes, Content Decides: Emergent Misalignment in Reward Models
Emergent Misalignment - the out of domain generalization of narrow harmful fine-tuning first shown by Betley et al. [2025] has been widely studied in language models but
- PaperCLARO: Clutter Aware Robot Orchestrator for Open-Vocabulary Grasping using VLM Agents
Robots that follow natural-language instructions unlock a wide range of autonomous applications in households, warehouses, and labs. Real-world environments are diverse a
- PaperVeil-Then-Reveal: Protecting PII Privacy via Reversible Pseudo-Anonymization in Zero-Trust User--LLM Interaction
Large language models (LLMs) increasingly process sensitive documents and personal information, yet sending prompts containing personally identifiable information (PII) t
- PaperReasoning Reranking with Semantic IDs as the Sole Item Representation
Reasoning rerankers write a rationale before ranking a candidate slate, and existing systems read item metadata to do so, even though generative recommenders increasingly
- PaperCausal Latent Workspaces for Looped Transformers
Reusing a Transformer block across depth increases computation without replicating its parameters, but successive passes have no dedicated state through which positions c
- PaperAnalysis of Binary O-type Star Systems Using Recurrent Neural Networks
This work presents an initial analysis of the estimation of effective temperature and surface gravity for simulated O-type binary systems using a recurrent neural network
- PaperSTRIDE: Evaluating Spatiotemporal Reasoning in Driving Edge Cases
In autonomous driving, perceiving surrounding objects is not enough: failing to understand how they move and interact over time can lead to dangerous decisions. Evaluatin
- PaperOri: Drift-Aware Streaming $k$-PCA for Very Low-Rank LLM Training
A prominent family of low-rank LLM optimizers, pioneered by GaLore, performs gradient-subspace projection: at each step, they project the gradient into a low-dimensional
- PaperPrune the Leaky Neurons: Mitigating Private Data Leakage in Fine-Tuned LLMs via Joint-Embedding-Guided Pruning
Fine-tuning large language models (LLMs) on proprietary records enables domain adaptation but introduces two challenges: (i) privacy leakage of memorized private data, su
- PaperSelf-Evolving Coding Agents via Harness-Policy Optimization
Large language model (LLM) agents have shown promising potential in coding tasks, and their performance is jointly determined by the policy model and the harness that med
- PaperNext Token or Vector? Learning How Far to Decode
Standard autoregressive decoding advances one token at a time, even when several upcoming tokens can be predicted together. We propose CADENCE (Context-Adaptive DEcoding)
- PaperAnytime Contracts for AI Services
AI services are prone to moral hazard, as model providers can silently route requests to cheaper, lower-quality models, and the inherent stochasticity of model outputs ma
- PaperWhen Can You Trust an Agent's Own Verifier? Stress-Testing Counterfactual Rationale Verification Under Search Pressure and Oracle Access
Automated agent design increasingly trusts a single score to decide whether a change is an improvement -- but a score optimized aggressively enough ceases to measure what
- PaperDirect Conditional Parameterization for N-Dimensional Splatting
N-dimensional splatting extends 3D Gaussian Splatting with view direction and time to model view-dependent and dynamic effects. Each primitive is lifted into a joint dist
- PaperReusing Calibration Gains across Model Representations
Scale calibration learns an update for one model representation. We study how much of that update can be reused by another representation of the same pretrained model. Ou
- PaperUnit-level aggregation breaks coverage in causal foundation models
Causal foundation models (CFMs) show promising results for treatment-effect estimation, with unit-level estimates that are competitive on standard benchmarks. Many causal
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.