AI & Machine Learning

Demonstrates that direct supervised alignment outperforms self-supervised pretraining for clinical outcome prediction in healthcare.

A red-teaming protocol that uses RL-driven 'profit' objectives to find structural exploits in AI agents instead of just prompt-injection vulnerabilities.

Contrastive Association Learning (CAL) successfully recovers functional gene associations from expression data where standard similarity metrics fail.

Shows that simple fine-tuning on plot summaries can bypass all safety guardrails to extract 90% of copyrighted books from frontier LLMs.

Identifies that in-context reasoning over pretraining knowledge only emerges after specific types of fine-tuning, not from pretraining alone.

Consistency under paraphrase in medical VLMs is a false proxy for reliability that hides models ignoring visual inputs entirely.

Pretrained Diffusion Transformers (DiTs) possess an intrinsic 'synchronization gap' where different features commit at specific, depth-localized layers.

Sensitivity to compression in Transformers spans five orders of magnitude, with early-layer MLP up-projections identified as catastrophic failure points.

The 'routing paradox' proves that selective attention requires the very pairwise computations it aims to replace, explaining why pure recurrent models fail at associative recall.

CLT-Forge democratizes mechanistic interpretability by providing an end-to-end library for training Cross-Layer Transcoders and generating feature attribution graphs.

Dream Diffusion Policy enables robots to survive severe OOD disturbances by detecting reality-imagination discrepancies and switching to an internal world model.

Cortical Policy introduces a dual-stream view transformer inspired by the human brain's dorsal and ventral pathways to solve complex robotic manipulation.

LongCat-Flash-Prover is a 560B MoE model that sets a new SOTA for open-weights formal reasoning, achieving a 97.1% pass rate on MiniF2F-Test.

Context-aware Visual Fine-tuning (CoVFT) allows a 7B MLLM to outperform its 13B counterpart by resolving optimization conflicts in vision encoders.

VAE tokenizers in Latent Diffusion Models create 'overly compact' manifolds that cause variance collapse, leading to unstable generative sampling.

Introduces 'Mixture of Chapters' to scale Transformer memory to 262K tokens without the quadratic cost of standard attention.

CounterScene endows generative world models with explicit counterfactual reasoning for safety-critical driving evaluation.

A training-free visual token pruning framework for Large Vision-Language Models that preserves geometric structure through subspace reconstruction.

Free Sinewich enables parameter-efficient multi-task learning using frequency-based weight modulation with near-zero overhead.

Reveals that state-of-the-art MLLMs fail to maintain stable spatial representations under simple counterfactual viewpoint changes.

LiFR-Seg achieves high-frame-rate semantic segmentation using low-frame-rate cameras by propagating features through asynchronous event streams.

Proposes multi-cluster memory for test-time adaptation, proving that a single unstructured memory pool is fundamentally insufficient for non-i.i.d. data streams.

ORACLE uses symbolic reasoning engines to verify intermediate reasoning steps in synthetic data generation, moving beyond simple answer-correctness filtering.

AlphaAdj uses a VLM to dynamically adjust Control Barrier Function parameters in real-time for safe and efficient robotic navigation.

BadGraph demonstrates that LLMs can generate universal adversarial attacks that exploit vulnerabilities in both GNN and PLM architectures on graph data.

SPECTRE-G2 is a unified anomaly detector that uses eight complementary signals to detect 'unknown unknown' structural anomalies.

Restores monotonic scaling in LLM tree search by replacing standard MCTS selection with Gumbel sampling and Sequential Halving.

A training-free system for 3D scene reconstruction and editing from sparse RGB images using 3D-aware diffusion models to fill geometric gaps.

Introduces the Neural Zeroth-order Kernel (NZK) to provide a theoretical foundation for training models without backpropagation.

Shows that a simple pruned adaptation module (PAM) outperforms complex SOTA foundation-model-based continual learning methods.

Demonstrates that entropy-based uncertainty is insufficient for safe selective prediction and proposes combining it with correctness probes.

Reframes plasticity loss in Reinforcement Learning as an optimization problem where networks get trapped in local optima of previous tasks.

Introduces Reward Sharpness-Aware Fine-Tuning (RSA-FT) to mitigate reward hacking in diffusion models without retraining reward models.

GIDE enables precise, training-free image editing for discrete Diffusion LLMs by introducing a novel Discrete Noise Inversion mechanism.

Prompt Replay speeds up GRPO training by selectively reusing 'medium difficulty' prompts to maximize learning signal in RL rollouts.

Repurposes a 2B-parameter latent video transformer as a differentiable physics simulator for urban wind flow optimization.

Provides the first empirical evidence of a 'Quality-Homogenization Tradeoff' where AI-assisted writing strips structural diversity from human thinking.

Challenges the widespread assumption that auxiliary dynamics supervision creates useful latent structures for robotics.

Proves that structured retrieval is exponentially more efficient than sequential context scanning for agentic reasoning.

Proposes replacing flat conversation histories with a tree-based architecture to solve 'logical context poisoning.'

Breaks the massive compute barrier for medium-range weather forecasting, training on a single consumer-grade GPU.

Enables multimodal models to self-evolve their reasoning without human labels or external reward models.

Replaces self-attention with Reaction-Diffusion PDEs as the predictive engine for world models.

Identifies architectural 'stream separation' as the key to making linear safety interventions effective.

An autonomous agent loop that optimizes GPU kernels to outperform human-expert and compiler-generated baselines.

Reconceptualizes human-agent interaction as dynamically generated software rather than just chat.

Exposes that LLMs solve complex puzzles via 'reduction' to known patterns rather than true epistemic reasoning.

Introduces AgentHER, a framework that salvages 'failed' agent trajectories by relabeling them as successful demonstrations for alternative goals.

ADARUBRIC generates task-specific evaluation rubrics on the fly, significantly outperforming static rubrics in human correlation and agent training outcomes.

TIDE is a post-training early-exit system that allows individual tokens to skip unnecessary layers, improving throughput by up to 8% with minimal calibration.