AI & Machine Learning

Exposes 'hidden clones' in VLM ensembles, where models from the same family share correlated errors that naive voting mechanisms fail to detect.

Proposes REAL, a Reinforcement Learning framework tailored for regression and ordinal scoring rather than simple binary accuracy.

Introduces a framework for LLM agents to autonomously evolve their policies and skill libraries during system idle time without retraining downtime.

A backbone-agnostic denoising objective that allows small GNNs to outperform large models pretrained on much larger supervised datasets in physical sciences.

Achieves high-performance online continual learning without the massive memory overhead of traditional experience replay buffers.

Internal activation probing detects LLM 'rationalization' more reliably than monitoring the model's own Chain-of-Thought (CoT).

A dynamic data pruning framework that cuts dense retriever training time by 50% while actually improving retrieval accuracy.

Automates the generation of synthetic machine learning challenges to train agents that can genuinely learn research skills from doing.

Alignment processes induce a 'normative bias' that makes LLMs worse at predicting real human behavior in strategic scenarios.

Enables reliable, training-free emotion steering in speech-generative audio models via direct manipulation of specific emotion-sensitive neurons.

A formal, graph-native memory architecture that treats agent memory as a versioned asset, dramatically outperforming Gemini 2.5 Pro on complex recall.

A framework to quantify and fix 'task steerability,' the common failure of robots to respond to new instructions while mid-task.

Achieves up to a 1,000x gain in RLHF data efficiency by using information-directed exploration and epistemic neural networks.

Introduces a reward framework that reduces LLM reasoning verbosity by optimizing for 'Information Density' via entropy reduction per step.

Shifts retrieval from static contrastive vector alignment to dynamic reasoning trajectories using a generative model (T1) and GRPO.

Identifies that reasoning-induced safety failures occur *during* Chain-of-Thought and proposes a shift to 'decide-then-reason' architectures.

Generates 9 million grid points of 3D spatiotemporal physical fields in seconds, a 10,000x speedup over traditional physics simulations.

Proposes a world model that jointly generates appearance and binocular geometry using an epipolar-aware attention mechanism.

Introduces FineViT and a 450M local caption dataset to solve the 'coarse perception' bottleneck in current CLIP-based encoders.

Provides a sheaf-theoretic proof that local causal consistency in generative models does not guarantee global counterfactual coherence.

Replaces quadratic self-attention with $O(N \log N)$ phase-native coupling for time-series, enabling massive context windows.

Introduces a paradigm for vision-language navigation that uses ubiquitously available semantic floor plans as global spatial priors.

Embeds invisible, agent-specific 'watermarks' into token distributions to enable forensic attribution and topology reconstruction in multi-agent systems.

Achieves an 80% reduction in Chain-of-Thought (CoT) tokens while slightly increasing reasoning accuracy.

Extends LLM context from 32K to 128K by teaching models to selectively skip global attention for ~80% of tokens.

Reduces hallucinations by teaching models 'epistemological humility'—the ability to admit they don't know something—using synthetic non-existent terms.

Develops a zero-watermarking framework that survives AI editing by leveraging invariant relations between image patches.

Unifies large-scale search, recommendation, and reasoning into a single self-contained LLM by treating item IDs as a distinct modality.

Video fine-tuning consistently degrades static image understanding in multimodal LLMs, revealing a zero-sum trade-off between spatial and temporal capabilities.

Introduces a Prompt-Free Universal Region Proposal Network (PF-RPN) that identifies objects in any domain without needing text or image exemplars.

FrescoDiffusion enables coherent, 4K image-to-video generation using a training-free, tiled diffusion method with precomputed latent priors.

Knowledge-Aware Active Learning (KA2L) uses latent space probing to identify what an LLM doesn't know and generates targeted synthetic questions.

Dense retrieval architectures are fundamentally flawed at detecting negation and contradictions due to 'Semantic Collapse' in vector space.

Edit-As-Act reframes 3D scene editing as a goal-regressive planning problem using symbolic action languages rather than purely generative pixel manipulation.

ARES demonstrates high-fidelity data reconstruction from large Federated Learning batches without requiring any architectural modifications to the model.

Mechanistic probing reveals a directional asymmetry in how LLMs encode hierarchy: hypernymy is redundant and resilient, while hyponymy is fragile and compact.

S-VGGT introduces structure-aware subscene decomposition to break the quadratic scaling bottleneck of 3D foundation models.

Introduces a framework to generate complex, non-linear environments with mathematically guaranteed ground-truth optimal policies for RL benchmarking.

DSS-GAN is the first generative adversarial network to use a Mamba (State Space Model) backbone for high-quality image synthesis.

VectorWorld enables stable, real-time 1km+ closed-loop world model rollouts for autonomous driving using diffusion flow on vector graphs.

REAL achieves extreme quadruped parkour agility that is robust even to a 1-meter visual blind zone.

FINER discovers that MLLMs are highly prone to hallucination when images contain fine-grained mismatches co-occurring with real elements.

Synthetic videos of simple geometric shapes are more effective than massive real-world datasets for teaching video-language models fundamental temporal reasoning.

Lifting 2D features into a volumetric representation for robot manipulation policies yields a 14.8% success rate improvement by solving the 2D-3D spatial reasoning mismatch.

A new self-refining surrogate framework enables neural models to simulate complex dynamical systems over arbitrarily long horizons without the standard failure mode of compounding error.

Massive activation outliers in Transformers are an adaptive response to 'gradient sinks' during training, rather than just an inference-time quirk.

The 'consensus trap' in label-free RL—where models reinforce their own systematic errors—can be broken by co-evolving the model in alternating generator and verifier roles.

In-context memory for LLMs is fundamentally unreliable due to compaction loss and goal drift, but structured 'Knowledge Objects' provide a 252x cheaper and 100% accurate alternative.

Anomaly detection can be performed directly using a primary model's internal neuron output ranges, eliminating the need for expensive external AD models.

Truncated backpropagation for video decoding reduces the memory cost of fine-tuning video diffusion models from linear to constant.