Skip to content
Tagged articles

NeurIPS 2026

46 articles · Page 1 of 1
Machine Heart
Machine Heart
Nov 20, 2026 · Artificial Intelligence

VLMs Prioritize Object Size Over Humans in Scene Understanding, NeurIPS 2026 Finds

A NeurIPS 2026 study reveals that vision-language models (VLMs) significantly differ from humans in scene understanding: VLMs over-rely on object size, centeredness, and low-level saliency, while humans naturally focus on people. The researchers introduce Counterfactual Semantic Saliency (CSS), a black-box evaluation method, and a dataset of 307 scenes with 1,306 counterfactual variants, showing all 19 tested VLMs fall short of human-level alignment, with size sensitivity being the primary driver of this gap.

Black-Box EvaluationCausal InterventionCounterfactual Semantic Saliency
0 likes · 13 min read
VLMs Prioritize Object Size Over Humans in Scene Understanding, NeurIPS 2026 Finds
Machine Heart
Machine Heart
Nov 20, 2026 · Artificial Intelligence

Massive Activations in LLMs Function as Gradient Regulators, Study Reveals

Researchers from Tsinghua and Peking University discover that massive activations in transformer models act as adaptive gradient regulators, with attention sinks creating gradient sinks that RMSNorm suppresses, revealing a backward-propagation mechanism linking attention concentration to activation scaling.

Attention SinkBackpropagationGradient Sink
0 likes · 11 min read
Massive Activations in LLMs Function as Gradient Regulators, Study Reveals
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Nov 20, 2026 · Artificial Intelligence

Forward-Only LLM Adaptation: NeurIPS 2026 Method Evolves Models During Inference

A NeurIPS 2026 paper from Lund University and Google DeepMind introduces a forward-only adaptation method for LLMs that uses angular concentration of SVD components during inference to achieve task-specific adaptation without backpropagation, reducing peak memory and increasing speed compared to gradient-based and exhaustive search baselines.

LLM adaptationNeurIPS 2026SVD
0 likes · 9 min read
Forward-Only LLM Adaptation: NeurIPS 2026 Method Evolves Models During Inference
Machine Heart
Machine Heart
Nov 20, 2026 · Artificial Intelligence

NeurIPS 2026: Forward-Only LLM Adaptation During Inference via SVD Angle Concentration

A NeurIPS 2026 paper introduces a forward-only adaptation method for LLMs that uses angle concentration of SVD components to prune ranks during inference without backpropagation, achieving lower peak memory and higher speedup than gradient-based and exhaustive search methods across diverse models and tasks.

LLM adaptationNeurIPS 2026SVD
0 likes · 9 min read
NeurIPS 2026: Forward-Only LLM Adaptation During Inference via SVD Angle Concentration
Machine Heart
Machine Heart
Nov 17, 2026 · Artificial Intelligence

HKU NeurIPS 2026: Implicit Advantage Symmetry Explains GRPO's Dual Bottlenecks

Hong Kong University researchers identify implicit advantage symmetry as the root cause of GRPO's poor exploration and difficulty adaptation, proposing A-GRAE to dynamically break symmetry and achieve simultaneous gains in Pass@1 accuracy and Pass@k diversity across math and multimodal benchmarks without extra compute.

A-GRAEGRPOLLM post-training
0 likes · 13 min read
HKU NeurIPS 2026: Implicit Advantage Symmetry Explains GRPO's Dual Bottlenecks
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Nov 17, 2026 · Artificial Intelligence

Diffusion LLMs Leak Less Than Autoregressive Models, But Finer Sampling Steps Increase Extraction Risk

Aalborg University researchers show diffusion language models leak less training data than autoregressive models at equal scale, but increasing sampling steps during generation significantly raises exact memorization extraction risk, as demonstrated on Enron email completion tasks with LLaDA-8B and matched 1.1B models.

Aalborg UniversityLLaDA-8BNeurIPS 2026
0 likes · 10 min read
Diffusion LLMs Leak Less Than Autoregressive Models, But Finer Sampling Steps Increase Extraction Risk
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Nov 16, 2026 · Artificial Intelligence

Diffusion vs. Autoregressive LLMs: Which Leaks More Training Data? Sampling Steps Dramatically Increase Memorization Risk

Aalborg University researchers show diffusion language models leak less training data than autoregressive models at equal scale, but finer sampling steps sharply raise exact memorization risk — LLaDA-8B's extraction success jumps 20× when moving from one-step to token-by-token generation.

Aalborg UniversityLLaDA-8BNeurIPS 2026
0 likes · 11 min read
Diffusion vs. Autoregressive LLMs: Which Leaks More Training Data? Sampling Steps Dramatically Increase Memorization Risk
Machine Heart
Machine Heart
Nov 15, 2026 · Artificial Intelligence

SkillMaster: LLM Agents That Autonomously Evolve Their Own Skills via Counterfactual Rewards

Tsinghua University's SkillMaster framework teaches LLM agents to create, update, and retain reusable skills through reinforcement learning, using counterfactual utility rewards and DualAdv-GRPO to jointly optimize task execution and skill management, achieving 98.7% on ALFWorld and 82.0% on WebShop with Qwen2.5-7B.

DualAdv-GRPOLLM agentsNeurIPS 2026
0 likes · 11 min read
SkillMaster: LLM Agents That Autonomously Evolve Their Own Skills via Counterfactual Rewards
Machine Heart
Machine Heart
Nov 15, 2026 · Artificial Intelligence

Finer Sampling Steps Boost Privacy Leakage in Diffusion LLMs, NeurIPS 2026 Finds

Aalborg University researchers present a generalized extraction framework showing diffusion language models leak less training data than autoregressive models at same scale, but finer sampling steps significantly increase exact memorization recovery, with LLaDA-8B showing a 20x increase in email extraction when switching from one-step to token-by-token generation.

LLaDANeurIPS 2026autoregressive models
0 likes · 11 min read
Finer Sampling Steps Boost Privacy Leakage in Diffusion LLMs, NeurIPS 2026 Finds
Machine Heart
Machine Heart
Nov 13, 2026 · Artificial Intelligence

NeurIPS 2026: HKUST's Visual-Native Agent Solves Image Reuse in Multimodal Deep Search

HKUST MMSense Lab introduces a visual-native agent framework that assigns unique IDs to images for tool chaining in multimodal deep search, and an on-policy data evolution method that iteratively refines question-generation rules using agent rollouts, boosting 8B and 30B model accuracy across eight benchmarks.

HKUST MMSense LabImage ReuseMultimodal Deep Search
0 likes · 20 min read
NeurIPS 2026: HKUST's Visual-Native Agent Solves Image Reuse in Multimodal Deep Search
Machine Heart
Machine Heart
Nov 9, 2026 · Artificial Intelligence

Touch-R1: RL-Powered Tactile Reasoning Resolves Vision-Touch Conflicts (NeurIPS 2026)

Touch-R1 introduces the first tactile-anchored physical reasoning model using reinforcement learning to enable cross-sensor tactile inference, correcting visual misjudgments by prioritizing tactile evidence, and achieves state-of-the-art results on the new TouchReason-Bench benchmark across nine metrics including physical property identification, ordinal reasoning, and cross-sensor consistency.

Cross-Sensor ConsistencyEmbodied AINeurIPS 2026
0 likes · 10 min read
Touch-R1: RL-Powered Tactile Reasoning Resolves Vision-Touch Conflicts (NeurIPS 2026)
Machine Heart
Machine Heart
Nov 8, 2026 · Artificial Intelligence

LCVN: Predicting Full Navigation Paths from One Frame and Language Instruction

The paper introduces LCVN, a language-conditioned visual navigation task where models predict complete action sequences from a single starting image and a language instruction, comparing a world-model-plus-policy pipeline against a unified autoregressive model on a new dataset with three instruction styles.

LCVNNeurIPS 2026autoregressive models
0 likes · 11 min read
LCVN: Predicting Full Navigation Paths from One Frame and Language Instruction
Machine Heart
Machine Heart
Nov 6, 2026 · Artificial Intelligence

NeurIPS 2026: Ascend RL Training System Hits 222% Speedup with Adaptive Scheduling

The Shenzhen Institute of Big Data and Huawei present ASP, an adaptive scheduling pipeline for multi-instance asynchronous RL training on Ascend 910B3 NPUs, eliminating padding, skewness, and sorting bubbles to achieve 222% higher generation throughput and 76% lower iteration time, validated at NeurIPS 2026 and deployed in telecom cutting training from three months to two.

Ascend NPULLMMindSpeed-RL
0 likes · 20 min read
NeurIPS 2026: Ascend RL Training System Hits 222% Speedup with Adaptive Scheduling
Machine Heart
Machine Heart
Nov 4, 2026 · Artificial Intelligence

RaPO: Retention-Aware Policy Optimization Fixes Catastrophic Forgetting in MLLMs

HKU researchers propose RaPO, a reinforcement fine-tuning method that adds a retention reward based on trajectory-level drift to prevent catastrophic forgetting in multimodal large language models during visual continual learning, achieving state-of-the-art results on five benchmarks with minimal forgetting.

Catastrophic ForgettingContinual LearningGRPO
0 likes · 16 min read
RaPO: Retention-Aware Policy Optimization Fixes Catastrophic Forgetting in MLLMs
SmartApe AI
SmartApe AI
Nov 3, 2026 · Artificial Intelligence

DexHoldem: HKU's Poker-Table Benchmark Unifies Robot Dexterity and Reasoning Evaluation

Hong Kong University and Yisheng Technology introduce DexHoldem, a real-robot benchmark using Texas Hold'em to test both dexterous manipulation (1,470 demos, 14 skills, UR10e+Shadow hand) and embodied perception/reasoning (36 questions, 14 model combos), with metrics TCR and SPSR revealing gaps between action success and scene preservation.

DexHoldemEmbodied AINeurIPS 2026
1 likes · 10 min read
DexHoldem: HKU's Poker-Table Benchmark Unifies Robot Dexterity and Reasoning Evaluation
Machine Heart
Machine Heart
Nov 2, 2026 · Artificial Intelligence

MemSkill: Evolving Memory Skills for Self-Improving Agents

MemSkill introduces memory skills as learnable, reusable modules that enable agents to continuously improve memory construction via task feedback and failure analysis, achieving state-of-the-art results on long-term dialogue and embodied interaction benchmarks with zero-shot transfer across models and tasks.

MemSkillNeurIPS 2026Recursive Self-Improvement
0 likes · 11 min read
MemSkill: Evolving Memory Skills for Self-Improving Agents
SmartApe AI
SmartApe AI
Oct 31, 2026 · Artificial Intelligence

MIPU: New RL Method Bridges LLM Training-Inference Gap

Researchers from Tianjin University and Alibaba propose MIPU, a reinforcement learning method that addresses training-inference mismatch in LLMs by directly optimizing inference-time performance, achieving higher accuracy and more stable training on Qwen3 models across math benchmarks.

LLM trainingMIPI PrincipleMIPU
0 likes · 11 min read
MIPU: New RL Method Bridges LLM Training-Inference Gap
Machine Heart
Machine Heart
Oct 29, 2026 · Artificial Intelligence

FAME: Multimodal Robot Exploration via Conditional Flow Matching for Active 3D Mapping

Tianjin University and Hefei University of Technology researchers propose FAME, a multimodal exploration framework using Conditional Flow Matching to generate multiple exploration anchors, combined with A* path planning, clustering, and hierarchical selection, achieving state-of-the-art coverage on AiMDoom and Matterport3D benchmarks with strong cross-dataset generalization.

Active 3D MappingConditional Flow MatchingCross-Dataset Generalization
0 likes · 12 min read
FAME: Multimodal Robot Exploration via Conditional Flow Matching for Active 3D Mapping
Machine Heart
Machine Heart
Oct 28, 2026 · Artificial Intelligence

NV-CoT: Continuous Coordinates Boost Visual Chain-of-Thought (NeurIPS 2026 Oral)

NV-CoT replaces discrete tokenized bounding boxes with continuous numerical coordinate prediction via four lightweight linear heads and a Laplace policy for reinforcement learning, raising region localization IoU from 47.3 to 59.5 and improving high-resolution VQA accuracy on V* Bench and HR-Bench under both supervised fine-tuning and GRPO.

Continuous CoordinatesMultimodal Large ModelsNV-CoT
0 likes · 11 min read
NV-CoT: Continuous Coordinates Boost Visual Chain-of-Thought (NeurIPS 2026 Oral)
Data Party THU
Data Party THU
Oct 28, 2026 · Artificial Intelligence

EchoChat: From Voice Perception to Empathetic Response in Speech Dialogue

EchoChat introduces a unified framework for empathetic speech dialogue that decomposes empathy into acoustic perception, Theory of Mind reasoning, and response generation, using Acoustic-Anchored Attention and step-decomposed credit assignment to improve understanding and response alignment, evaluated on new datasets EchoDialogue-400K and EchoEval.

Acoustic-Anchored AttentionEchoChatEchoDialogue-400K
0 likes · 10 min read
EchoChat: From Voice Perception to Empathetic Response in Speech Dialogue
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Oct 27, 2026 · Artificial Intelligence

Refusal ≠ Safety: ReasoningShield Exposes Chain-of-Thought Security Blind Spots

Researchers from Shanghai AI Lab and Fudan University introduce ReasoningShield, the first benchmark and moderation models for chain-of-thought safety, showing that final answer safety doesn't guarantee reasoning trace safety, and achieving SOTA on reasoning trace moderation with 91.8% F1.

AI safetyNeurIPS 2026ReasoningShield
0 likes · 15 min read
Refusal ≠ Safety: ReasoningShield Exposes Chain-of-Thought Security Blind Spots
Machine Heart
Machine Heart
Oct 24, 2026 · Artificial Intelligence

TabClustPFN: Out-of-the-Box Tabular Clustering with Probabilistic Cluster Count

Researchers from Renmin University, Rutgers, NUS, and MBZUAI introduce TabClustPFN, a prior-data fitted network that performs zero-shot clustering on tabular data via a single forward pass, automatically estimating the number of clusters and providing a probability distribution over candidate cluster counts, achieving competitive performance on 44 real-world datasets without per-dataset training.

Cluster Count EstimationNeurIPS 2026PFN
0 likes · 10 min read
TabClustPFN: Out-of-the-Box Tabular Clustering with Probabilistic Cluster Count
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Oct 24, 2026 · Artificial Intelligence

ReasoningShield: Why Final Answer Safety Isn't Enough for Chain-of-Thought Models

ReasoningShield introduces the first chain-of-thought safety moderation benchmark with 9.2K samples across 10 risk categories, training 1B/3B models that achieve 91.8% F1 on reasoning traces—outperforming GPT-4o (87.8%) and LlamaGuard-4-12B (56.2%)—while localizing risk evidence to specific reasoning steps.

AI alignmentLLM safetyNeurIPS 2026
0 likes · 13 min read
ReasoningShield: Why Final Answer Safety Isn't Enough for Chain-of-Thought Models
Machine Heart
Machine Heart
Oct 24, 2026 · Artificial Intelligence

VAST: Adaptive Horizon Selection for Long-Horizon RL via Value Stitching

Researchers from HKU and Tsinghua propose VAST, an offline RL framework that adaptively chooses time horizons for value updates by stitching variable-length trajectory segments, improving long-horizon decision-making across 50 OGBench tasks.

Adaptive Horizon SelectionLong-Horizon RLNeurIPS 2026
0 likes · 10 min read
VAST: Adaptive Horizon Selection for Long-Horizon RL via Value Stitching
Machine Heart
Machine Heart
Oct 22, 2026 · Artificial Intelligence

SpanUQ: Span-Level LLM Uncertainty Estimation 10-20x Faster Than Sampling

This NeurIPS 2026 paper introduces Span-Level Uncertainty Estimation (SLUE) and SpanUQ, a lightweight probe that detects semantic spans and quantifies their uncertainty in a single forward pass, achieving 10-20x speedup over sampling-based methods while providing fine-grained, actionable uncertainty signals for downstream decision-making.

LLM UncertaintyNeurIPS 2026Probe Model
0 likes · 31 min read
SpanUQ: Span-Level LLM Uncertainty Estimation 10-20x Faster Than Sampling
Machine Heart
Machine Heart
Oct 22, 2026 · Artificial Intelligence

ReGDiff: Guided Diffusion in Regulated Latent Space for Metamaterial Discovery

ReGDiff introduces a two-step method — RAS for latent space regulation and SRR for short-range repulsion during sampling — to generate geometrically valid, novel, and diverse metamaterial voxel structures, outperforming baselines on MetaTruss and MetaShell datasets with significant improvements in geometric rationality, novelty, and diversity.

AI for ScienceGenerative AIMetaTruss dataset
0 likes · 14 min read
ReGDiff: Guided Diffusion in Regulated Latent Space for Metamaterial Discovery
Machine Heart
Machine Heart
Oct 21, 2026 · Artificial Intelligence

RVCBench at NeurIPS 2026: Benchmarking 18 Voice Cloning Models for Real-World Robustness

RVCBench introduces a comprehensive benchmark evaluating 18 voice cloning models across 18 robustness tests covering input shifts, generation challenges, output distortions, and adversarial audio perturbations, revealing that clean-condition performance does not predict real-world reliability and that model architecture matters more than size.

NeurIPS 2026RVCBenchadversarial audio
0 likes · 22 min read
RVCBench at NeurIPS 2026: Benchmarking 18 Voice Cloning Models for Real-World Robustness
Machine Heart
Machine Heart
Oct 20, 2026 · Artificial Intelligence

WorldMemArena: Benchmarking Multimodal Agent Memory in Action-World Loops

WorldMemArena, a NeurIPS 2026 benchmark from UCSB, Stanford, ETH Zurich, and others, evaluates multimodal agent memory across write, maintain, retrieve, and use stages in dynamic action-world loops, showing high recall rates (86%) don't guarantee correct answers (50%).

Multimodal Agent MemoryNeurIPS 2026WorldMemArena
0 likes · 9 min read
WorldMemArena: Benchmarking Multimodal Agent Memory in Action-World Loops
Machine Heart
Machine Heart
Oct 20, 2026 · Artificial Intelligence

VLMs Encode 3D Scene Topology in Latent Space: NeurIPS 2026 Spotlight Findings

University of Pittsburgh researchers show that vision-language models internally represent 3D scene topology in middle-layer latent spaces, revealed by separating appearance attributes and visualizing spatial structure; Dirichlet energy quantifies neighborhood preservation, and fine-tuning with this loss improves spatial reasoning on benchmarks like VSI-Bench.

3D Scene UnderstandingDirichlet EnergyInterpretability
0 likes · 12 min read
VLMs Encode 3D Scene Topology in Latent Space: NeurIPS 2026 Spotlight Findings
Machine Heart
Machine Heart
Oct 18, 2026 · Artificial Intelligence

DR-Rubric: Deep Research as Rubric for Open-Ended Reinforcement Learning

Xiaohongshu and Fudan University propose DR-Rubric, a framework where models perform deep research to gather evidence and synthesize atomic constraints as rubrics for reinforcement learning rewards, achieving competitive results on six benchmarks with only 1,000 training samples while revealing non-monotonic bootstrap dynamics and reward polarization as a stopping signal.

DR-RubricDeep ResearchGRPO
0 likes · 21 min read
DR-Rubric: Deep Research as Rubric for Open-Ended Reinforcement Learning
Machine Heart
Machine Heart
Oct 16, 2026 · Artificial Intelligence

STILL: Content-Aware Intra-Layer Hybrid Attention for Efficient LLM Linearization

STILL introduces a content-aware intra-layer hybrid attention mechanism that routes tokens to Softmax or linear attention based on self-saliency scores computed locally, preserving pre-trained norm structure via NP-Map, achieving 80% memory reduction and 83% prefill speedup with only 0.04B training tokens.

Efficient TransformersIntra-Layer Hybrid AttentionLLM Linearization
0 likes · 20 min read
STILL: Content-Aware Intra-Layer Hybrid Attention for Efficient LLM Linearization
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Oct 16, 2026 · Artificial Intelligence

A3 Framework: 14B CLI Agent Beats 235B Model via Structured Action Credit Assignment

Fudan and SJTU researchers open-source A3, a reinforcement learning framework that uses AST-based structured credit assignment to train a 14B CLI agent achieving 24.6% exact match on ShellOps, doubling baselines, and outperforming a 235B model on out-of-distribution tasks with minimal computational overhead.

CLI agentsCredit AssignmentNeurIPS 2026
0 likes · 18 min read
A3 Framework: 14B CLI Agent Beats 235B Model via Structured Action Credit Assignment
Machine Heart
Machine Heart
Oct 16, 2026 · Artificial Intelligence

FlowMAS: AI Teams Learn to Self-Organize via GFlowNets

FlowMAS, a NeurIPS 2026 paper, uses Generative Flow Networks with curiosity-driven and information-theoretic rewards to automatically generate diverse, efficient multi-agent workflow topologies, outperforming baselines across six benchmarks with far lower computational cost.

Automated Architecture DesignCuriosity-Driven ExplorationGFlowNets
0 likes · 11 min read
FlowMAS: AI Teams Learn to Self-Organize via GFlowNets
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Oct 15, 2026 · Artificial Intelligence

NeurIPS 2026 Productivity Rankings: Open-Source Agent Reveals Two Different Answers

An analysis of NeurIPS 2026 acceptance data using the open-source PilotDeck 2.0 agent reveals Tsinghua leads in institutional participation while overseas institutions dominate high-productivity authors, alongside trends showing 3.4x submission growth, Benchmark papers dominating, and Agent research surging 2.42x.

AgentOSNeurIPS 2026PilotDeck 2.0
0 likes · 9 min read
NeurIPS 2026 Productivity Rankings: Open-Source Agent Reveals Two Different Answers
JD Retail Technology
JD Retail Technology
Oct 15, 2026 · Artificial Intelligence

RA-CFGCache: Risk-Aligned Caching for CFG-Guided Diffusion Models

RA-CFGCache introduces a risk-aligned caching framework for classifier-free guided diffusion models that jointly models cross-branch error alignment and timestep-dependent error propagation, achieving superior efficiency-fidelity trade-offs on FLUX.1-dev, Wan2.1, and CogVideoX while remaining compatible with existing cache estimators.

Classifier-Free GuidanceGenerative AIModel Acceleration
0 likes · 19 min read
RA-CFGCache: Risk-Aligned Caching for CFG-Guided Diffusion Models
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Oct 14, 2026 · Artificial Intelligence

TokenRouter: Efficient Token-Level LLM Routing via Async Handoffs & Delayed Batching

This article analyzes TokenRouter, a NeurIPS 2026 system that enables efficient token-level LLM routing through a request-centric programming interface, asynchronous model handoffs with state preservation, and throughput-optimized delayed batching, demonstrating 2-64x throughput gains over baselines across multiple routing algorithms and workloads.

LLM servingMarkov chain modelNeurIPS 2026
0 likes · 30 min read
TokenRouter: Efficient Token-Level LLM Routing via Async Handoffs & Delayed Batching
Machine Heart
Machine Heart
Oct 14, 2026 · Artificial Intelligence

Apple's LensVLM: Compress Long Text to Images, Zoom In for Details

Apple and Duke University propose LensVLM, a vision-language model that compresses long documents into images for efficient browsing, then lets the model selectively magnify relevant pages by retrieving original text, achieving 68.9% accuracy at 4.3x effective compression on seven QA benchmarks, nearing full-text performance while reducing latency and GPU costs.

LensVLMNeurIPS 2026effective compression rate
0 likes · 11 min read
Apple's LensVLM: Compress Long Text to Images, Zoom In for Details
Amap Tech
Amap Tech
Oct 12, 2026 · Artificial Intelligence

Amap's 16 NeurIPS 2026 Papers: Multimodal LLMs, Spatial Intelligence & Visual Reasoning

Amap had 16 papers accepted at NeurIPS 2026, covering multimodal large models, spatial intelligence, visual reasoning, and reinforcement learning, with highlights including a decomposed verifier for generative world modeling, gradient projection for continual multimodal learning, map-free transit route generation, and benchmarks for coding agents and travel planning.

3D reconstructionEmbodied AIMultimodal Large Models
0 likes · 30 min read
Amap's 16 NeurIPS 2026 Papers: Multimodal LLMs, Spatial Intelligence & Visual Reasoning
Machine Heart
Machine Heart
Oct 12, 2026 · Artificial Intelligence

TerraVis: Evaluating World Consistency in Text-to-Image Generation

TerraVis introduces a systematic framework for evaluating world consistency in AI-generated images, covering 18 issue types across object, interaction, and scene levels, validated on 13,500 human annotations across five models.

AI-generated imagesNeurIPS 2026benchmark
0 likes · 15 min read
TerraVis: Evaluating World Consistency in Text-to-Image Generation
SmartApe AI
SmartApe AI
Oct 11, 2026 · Artificial Intelligence

NeurIPS First IML Oral: PAL Boosts Cross-Domain F1 by 10.3%

Sichuan University researchers propose PAL, a two-stage pairwise artifacts learning framework, and the EditGroup-45K dataset to explicitly decouple manipulation artifacts from semantic features, achieving a 10.3% cross-domain F1 improvement and the first NeurIPS Oral in image manipulation localization.

Artifact DisentanglementComputer VisionCross-Domain Generalization
0 likes · 11 min read
NeurIPS First IML Oral: PAL Boosts Cross-Domain F1 by 10.3%
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Oct 8, 2026 · Artificial Intelligence

SAGE Corrects Long-Horizon Reasoning Drift via Structural Guidance, 8x AC Verification

NeurIPS 2026 paper SAGE introduces structural guidance via Symbolic Closure Analysis to fix long-horizon reasoning biases, using algebraic sparsification and hyperbolic distance feedback during training, outperforming baselines on 12 benchmarks and achieving nearly 8x Lean verification pass rate on Andrews-Curtis tasks.

Algebraic SparsificationAndrews-CurtisHyperbolic Space
0 likes · 16 min read
SAGE Corrects Long-Horizon Reasoning Drift via Structural Guidance, 8x AC Verification
Machine Heart
Machine Heart
Oct 7, 2026 · Artificial Intelligence

VisInteract: Recovering User Intent in Text-to-Vis via Interactive MCTS Search

VisInteract introduces a dynamic interactive Text-to-Vis paradigm with the VisInteract-Bench benchmark and Vis-MCTS method, using Monte Carlo Tree Search with progressive widening, cross-path memory, and dimension-aware reward decomposition to recover user intent from imperfect queries, achieving 51–57% Merge Task Score on 1,098 samples across 11 databases.

Imperfect QueriesMonte Carlo Tree SearchNeurIPS 2026
0 likes · 18 min read
VisInteract: Recovering User Intent in Text-to-Vis via Interactive MCTS Search
Machine Heart
Machine Heart
Oct 7, 2026 · Artificial Intelligence

SAGE: Topological Guidance Mitigates Long-Horizon Reasoning Biases, 8x Lean Pass Rate

Researchers from Virginia Tech, UW-Madison, and Dartmouth introduce SAGE, a post-training method that uses symbolic closure analysis to diagnose exploration and accumulation biases in long-horizon reasoning, applying algebraic sparsification and hyperbolic structure guidance to improve sampling and provide early feedback, achieving near 8x Lean verification pass rate on Andrews-Curtis tasks and outperforming baselines across 12 benchmarks.

Andrews-CurtisLarge Language ModelsLean verification
0 likes · 14 min read
SAGE: Topological Guidance Mitigates Long-Horizon Reasoning Biases, 8x Lean Pass Rate