Skip to content

Artwork for Eye on AI Weekly Research Watch

TechnologyNewsTech News

Eye on AI Weekly Research Watch

Craig Spencer Smith

Weekly, digestible podcast explainers of significant research papers

95 episodes
Avg 2 min
English

Episodes 95

Newest Oldest Longest

All20 Unplayed20 In progress0 Played0

Counted on this page — what you have heard stays on this device, so it is not something the list can be paged by.

October 7 · 2 min
HazardWeaver: Scientific Route Selection for Hazard Analysis Agents
Natural hazard analysis requires choosing scientific methods that are both appropriate for an event and executable with available data and tools, and those choices may need revising as evidence emerges. HazardWeaver frames this as state-dependent route se
October 7 · 2 min
When a Correct Reward Is Not Enough: Diagnosing and Guiding PPO in an Analytically Solved Broker-Trader Game
Reinforcement learning is increasingly applied to financial control, so this paper uses an analytically solved continuous-time broker–trader game to diagnose PPO. A PPO agent replaces the broker and sets trading speed. With no uninformed flow it approache
October 7 · 2 min
Low-Cost Video-Time Priors as a Strong Baseline for EEG-fNIRS Emotion Regression on Familiar Videos
Continuous emotion regression estimates a viewer's moment-to-moment valence and arousal while watching video. For familiar videos, the authors find that a simple prior based on which video is playing and the time within it is a strong, low-cost baseline.
October 7 · 2 min
Depth as Time in One-Step Generative Models
One-step generators compress multi-step diffusion into a single forward pass, raising the question of what happens to the denoising trajectory. The authors observe "depth as time": denoising unfolds across network layers and can be recovered by decoding i
October 7 · 2 min
NeutronGym: Physics-Graded Neutron Instrument Design for LLM Agents
Instrument design tests whether language-model agents can apply physics rather than recall it. NeutronGym is an executable environment for neutron instrument design: agents build instruments through validating tools, McStas ray-traces them, and a graded l
October 7 · 2 min
Credit Where It Matters: Dependency-Aware Policy Optimization for Terminal Agents
Terminal-using agents trained with reinforcement learning handle multi-step coding and debugging, but standard credit assignment ignores that later commands depend on earlier outputs, so training signals can land on irrelevant steps. DepGPO builds a comma
October 7 · 2 min
LoGo: Local-Global Rewards for Consistent Long-Horizon Video Generation
Camera-controlled video models struggle with 3D inconsistency over long horizons: objects vanish or scene structure shifts as the camera moves. Post-training with a single scalar reward gives poor credit assignment for these local errors. LoGo blends glob
October 7 · 2 min
Do Large Language Models Know Colombian Law? A Reliability Benchmark for the Colombian Legal System
LLMs are increasingly used in legal work, yet their reliability outside the United States is poorly documented. This expert-validated benchmark has 1,042 items across ten areas of law and three formats, and was used to test 15 models. Closed-question accu
October 7 · 2 min
On-Board Anomaly Detection for Efficient Marine Environmental Monitoring
Oil spills, algal blooms, and sediment floods harm marine ecosystems, and satellites could flag them early, but downlink bandwidth and onboard compute are limited. The authors propose a pipeline for multiand hyperspectral satellites: a self-supervised enc
October 7 · 3 min
MRVQ: One Resident Index for Dimension- and Rate-Elastic Vector Search
Dense-retrieval services must adapt embedding dimension and index bit rate as latency, quality, and memory budgets shift, but maintaining separate quantized indices for each setting is memory-hungry. Matryoshka Residual Vector Quantization (MRVQ) is a pos
October 7 · 2 min
Revisiting Input Time-frequency Representations in Multi-pitch Estimation for Vocal Ensembles
Estimating several simultaneous pitches in vocal ensembles is difficult because singers' ranges and harmonics overlap. Many models use harmonic constant-Q transform (HCQT) inputs for frequency-adaptive resolution, though feature extraction is expensive. T
October 7 · 2 min
FrugalEvo: Towards Cost-Aware LLM-Guided Program Evolution
LLM-guided evolutionary methods like AlphaEvolve tackle hard optimization problems, but they are usually judged on gain per iteration rather than per dollar. FrugalEvo pairs a stronger, costlier LLM that proposes solution strategies with a cheaper one tha
October 7 · 2 min
Transcriptome-informed multi-modal AI for predicting neoadjuvant therapy response from breast cancer biopsies
Predicting whether breast cancer patients will respond to neoadjuvant therapy is hard because labeled clinical data is scarce. This two-stage model first learns to infer gene expression from histopathology images, trained on 8,742 patients across 32 cance
October 7 · 2 min
EyeRobot 2.0: Active Gaze for Precise Manipulation without Wrist Cameras
Wrist cameras are common in robot manipulation but get occluded and add hardware complexity. Inspired by human vision, EyeRobot 2.0 uses a single stereo camera that physically swivels two viewpoints to fixate on a 3D point, processing the image center fov
October 7 · 2 min
What Should World Models Forget? Stratified Retention for Continual Adaptation
Continual learning normally treats forgetting as failure, but world models predict an environment that changes, so some old knowledge should be discarded. The authors argue for retention stratified by invariance timescale: invariants like physics and obje
October 7 · 2 min
4DCodeBench: Benchmarking Agents on Inverse Graphics of Dynamic Scenes
Reconstructing dynamic scenes usually means producing meshes or point clouds, but 4DCodeBench asks agents to write executable graphics programs from video. Agents must abstract scene structure and dynamics, for example by implementing physical simulations
October 7 · 2 min
Less Decoder is More Encoder: Geometric Representation Learning from Novel View Synthesis
Novel view synthesis should teach models about 3D structure, yet encoderbased approaches produce weak representations. The authors blame two architectural choices: decoders that are too spatially expressive, which dilute the encoder's role, and pixel-spac
October 7 · 3 min
The Pain Axis: LLMs Represent Self-Directed Harm and Act on It
Across 25 open-weight models from 2B to 72B parameters, the authors find a linear direction that represents pain separately from fear, sadness and general negativity. It responds to harm aimed at the model itself, not to suffering by the user. Pushing act
October 7 · 2 min
Kandinsky 6.0 Video: Foundation Models for Synchronized Video and Audio Generation
Kandinsky 6.0 Video generates 5-second clips with synchronized 44 kHz audio, including lip-sync, from text or an image, and upscales them to 1920x1080. It comes in two sizes, 3B (Lite) and 29B (Pro). A dual-stream CrossDiT links a pretrained video stream
October 7 · 2 min
Truly Subquadratic 3SUM and Truly Subcubic APSP via Triangles in Sparse Lopsided Graphs
The authors give deterministic algorithms for 3SUM in O(n^1.9992) time and all-pairs shortest paths in O(n^2.9995) time, the first polynomial improvements over the textbook bounds for either problem. That refutes the 3SUM and APSP hypotheses. Through know

Showing 1–20 of 95 episodes